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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nuest
    -0.07
     billionaires
    -0.06
    _frac
    -0.06
    nesení
    -0.06
     غذ
    -0.06
    283
    -0.06
    机械
    -0.06
     bladder
    -0.06
    esity
    -0.06
    085
    -0.06
    POSITIVE LOGITS
    <Array
    0.08
     після
    0.06
     شهر
    0.06
    _namespace
    0.06
    _construct
    0.06
    _almost
    0.06
    '>{
    0.06
    สาร
    0.06
    ersion
    0.06
    {{--
    0.06
    Act Density 0.741%

    No Known Activations