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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects boilerplate autogenerated-code header comments, e.g. lines like “// Code generated by …”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tanks
    -0.07
     bức
    -0.07
     Vak
    -0.06
    -center
    -0.06
     Spartan
    -0.06
    _successful
    -0.06
    /format
    -0.06
    ención
    -0.06
    _parent
    -0.06
    -readable
    -0.06
    POSITIVE LOGITS
    cea
    0.07
    imo
    0.06
     shrugged
    0.06
    769
    0.06
    _CHAR
    0.06
     bağlantı
    0.06
    ọng
    0.06
    _s
    0.06
     underscores
    0.06
    겠습니다
    0.06
    Act Density 0.001%

    No Known Activations