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

    Neuronpedia

    INDEX
    Explanations

    ->

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phin
    -0.07
    wid
    -0.07
    ника
    -0.06
    bei
    -0.06
    (ch
    -0.06
     Estate
    -0.06
     bacon
    -0.06
     estr
    -0.06
     razor
    -0.06
     학교
    -0.06
    POSITIVE LOGITS
    �
    0.07
     고객
    0.07
    �回
    0.07
     моря
    0.06
    发行
    0.06
     histo
    0.06
    逸
    0.06
     reife
    0.06
     نمود
    0.06
     구매
    0.06
    Act Density 0.006%

    No Known Activations