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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    qe
    -0.07
    очно
    -0.06
    .Dense
    -0.06
     гаран
    -0.06
    ('/')↵
    -0.06
     khả
    -0.06
    empt
    -0.06
    ischen
    -0.06
    ador
    -0.06
     Wong
    -0.06
    POSITIVE LOGITS
    ấc
    0.07
     �
    0.06
    ازند
    0.06
    Ipv
    0.06
    |r
    0.06
    SM
    0.06
    龄
    0.06
    javax
    0.06
     بودن
    0.06
     dvě
    0.06
    Act Density 0.008%

    No Known Activations