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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뺘
    -0.07
    院子
    -0.07
     прог
    -0.07
     Scale
    -0.06
    .Ac
    -0.06
     호
    -0.06
    -answer
    -0.06
     Cec
    -0.06
    走上
    -0.06
    Van
    -0.06
    POSITIVE LOGITS
    ercul
    0.08
    зов
    0.07
     '.';↵
    0.07
     игры
    0.07
     plentiful
    0.07
    囵
    0.07
    뉨
    0.07
    braska
    0.07
     aliens
    0.07
    UDA
    0.06
    Act Density 0.020%

    No Known Activations