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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    指定
    -0.07
    tw
    -0.06
     grabbed
    -0.06
     cum
    -0.06
    icz
    -0.06
     تقس
    -0.06
    位于
    -0.06
    Pedido
    -0.06
    GN
    -0.06
     assessments
    -0.06
    POSITIVE LOGITS
     for
    0.10
     FOR
    0.10
    —for
    0.09
    for
    0.09
     For
    0.08
     kidd
    0.08
    .for
    0.07
     برای
    0.07
    FOR
    0.07
    lya
    0.07
    Act Density 0.031%

    No Known Activations