Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act-logits · gemini-2.0-flash

    system or metadata tokens and XML/special formatting markers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @kdearsty

    ;

    np_max-act · deepseek-v3Triggered by @tatsatx

    The neuron is looking for code-related segments that involve variable assignments or updates, particularly focusing on the assignment of values to variables in programming contexts.

    oai_token-act-pair · deepseek-v3Triggered by @tatsatx
    New Auto-Interp
    Negative Logits
     באמצ
    -0.09
     Coch
    -0.08
     Priority
    -0.08
     Medium
    -0.08
     Commit
    -0.08
    323
    -0.08
     Commitment
    -0.08
     Serial
    -0.08
     Mis
    -0.08
     Comfort
    -0.08
    POSITIVE LOGITS
    маган
    0.08
     quantify
    0.08
    纸
    0.08
    ித்து
    0.08
     sharpen
    0.08
     şi
    0.08
    urban
    0.08
     extraordinarily
    0.08
    subtract
    0.08
     outrageous
    0.08
    Act Density 0.000%

    No Known Activations