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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiplic
    -0.07
    aison
    -0.07
     indice
    -0.07
    鞭
    -0.07
     unl
    -0.06
    창
    -0.06
    马路
    -0.06
    烦
    -0.06
     Tmax
    -0.06
    ул
    -0.06
    POSITIVE LOGITS
     interrog
    0.07
     squ
    0.07
     Audrey
    0.07
    _CONFIG
    0.07
    .rev
    0.07
    probably
    0.07
    .fs
    0.07
     ornaments
    0.07
    /datatables
    0.06
    ycastle
    0.06
    Act Density 0.056%

    No Known Activations