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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amplify
    -0.07
     ngày
    -0.07
     email
    -0.07
    contre
    -0.07
    .getInt
    -0.07
    广州
    -0.06
     differs
    -0.06
    iddle
    -0.06
    .getById
    -0.06
    羹
    -0.06
    POSITIVE LOGITS
    Calculator
    0.08
     Atat
    0.08
    Cumhurbaşkanı
    0.07
    轳
    0.07
     Bank
    0.07
     respectable
    0.07
    نتائ
    0.07
     politicians
    0.07
    مفاوض
    0.07
    Court
    0.06
    Act Density 0.008%

    No Known Activations