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

    Neuronpedia

    INDEX
    Explanations

    variables followed by inline code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.28
    m
    1.11
    in
    1.11
    l
    1.07
    r
    1.05
    a
    1.01
    u
    1.00
    ل
    0.95
    n
    0.94
    er
    0.94
    POSITIVE LOGITS
    idding
    0.68
    Какой
    0.66
    ourse
    0.64
    ussels
    0.62
    arganya
    0.62
    ould
    0.61
    enean
    0.61
    हमारे
    0.61
    ೈ
    0.61
    Какие
    0.60
    Act Density 0.435%

    No Known Activations