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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ารณ
    -0.07
    mux
    -0.06
     Ming
    -0.06
    руют
    -0.06
    .dark
    -0.06
     syrup
    -0.06
     lux
    -0.06
    umeric
    -0.06
    ць
    -0.06
    ò
    -0.06
    POSITIVE LOGITS
     excluded
    0.07
    stanov
    0.06
    OnInit
    0.06
    :date
    0.06
    禁止
    0.06
    ,bool
    0.06
    _BC
    0.06
    <bool
    0.06
     Alv
    0.06
    伴
    0.06
    Act Density 0.021%

    No Known Activations