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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens associated with statistical or demographic figures (e.g., census numbers and percentages).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    tor
    -0.07
    廷
    -0.07
     surgeries
    -0.06
    да
    -0.06
     Arap
    -0.06
     충
    -0.06
    oline
    -0.06
     กรกฎาคม
    -0.06
    .generate
    -0.06
     nef
    -0.06
    POSITIVE LOGITS
    .'),↵
    0.07
    'b
    0.07
    を持
    0.07
    -Agent
    0.07
    ").↵↵
    0.06
    -ball
    0.06
    %=
    0.06
    _running
    0.06
    ومی
    0.06
    =
    0.06
    Act Density 0.021%

    No Known Activations