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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cyn
    -0.07
     Defaults
    -0.07
     будів
    -0.07
    --
    -0.06
    976
    -0.06
    (or
    -0.06
    toLowerCase
    -0.06
    チーム
    -0.06
    —if
    -0.06
    [d
    -0.06
    POSITIVE LOGITS
    ="//
    0.07
    .white
    0.07
    ()
↵
↵
    0.07
    '
    0.07
    °
    0.07
    .↵
    0.06
    >↵
    0.06
    .width
    0.06
    -elements
    0.06
    ์↵
    0.06
    Act Density 0.190%

    No Known Activations