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

    Neuronpedia

    INDEX
    Explanations

    conject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Float
    -0.07
    compat
    -0.07
    ArgumentException
    -0.06
    %f
    -0.06
    gas
    -0.06
    (padding
    -0.06
    865
    -0.06
    /io
    -0.06
     corners
    -0.06
    ツ
    -0.06
    POSITIVE LOGITS
    .console
    0.08
    Principal
    0.06
     kapat
    0.06
    编辑
    0.06
    abaj
    0.06
    ampilkan
    0.06
     lesbisk
    0.06
     customize
    0.06
    assignments
    0.06
     вход
    0.06
    Act Density 0.006%

    No Known Activations