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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron flags code‐like syntax, activating on programming tokens such as function calls, method/property accessors, operators, and punctuation rather than ordinary prose.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pinterest
    -0.07
     ErrorCode
    -0.06
     해당
    -0.06
    seq
    -0.06
    ่เป
    -0.06
     refs
    -0.06
    src
    -0.06
    鑑
    -0.06
     �
    -0.06
     rer
    -0.06
    POSITIVE LOGITS
    unge
    0.07
    -faced
    0.07
     implicated
    0.07
    mostly
    0.06
     connector
    0.06
    Reflect
    0.06
    uluğ
    0.06
     etiqu
    0.06
     families
    0.06
    ган
    0.06
    Act Density 0.049%

    No Known Activations