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

    Neuronpedia

    INDEX
    Explanations

    buffer

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (i.e. number tokens, especially floating-point constants) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    انگ
    -0.07
     racist
    -0.06
     ACL
    -0.06
    _By
    -0.06
    _PARSER
    -0.06
     золот
    -0.06
    lü
    -0.06
     LANG
    -0.06
    ouflage
    -0.06
     PDO
    -0.06
    POSITIVE LOGITS
     wishing
    0.08
    Regardless
    0.07
     Carn
    0.07
    .Rendering
    0.07
    .feature
    0.06
    ισμός
    0.06
     Correspond
    0.06
     continuously
    0.06
     있던
    0.06
     notorious
    0.06
    Act Density 0.007%

    No Known Activations