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

    Neuronpedia

    INDEX
    Explanations

    SO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kel
    -0.07
    kre
    -0.07
    岙
    -0.07
    練
    -0.07
     مواض
    -0.07
     Chronicle
    -0.07
    سفر
    -0.07
    ﮩ
    -0.06
     CreateMap
    -0.06
    änn
    -0.06
    POSITIVE LOGITS
    mx
    0.07
    _VARIABLE
    0.07
    Conditional
    0.07
    _clients
    0.07
    惊
    0.07
    因子
    0.07
     humble
    0.07
    频
    0.07
    pressor
    0.07
    .collect
    0.07
    Act Density 0.012%

    No Known Activations