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

    Neuronpedia

    INDEX
    Explanations

    outputting "undefined"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    altern
    0.66
    ac
    0.65
    wooden
    0.64
    are
    0.63
    colorful
    0.62
    him
    0.61
     फैलता
    0.61
    с
    0.60
    comme
    0.60
    ARE
    0.59
    POSITIVE LOGITS
     output
    0.67
     el
    0.66
     hodnot
    0.63
    ادي
    0.62
    ى
    0.62
    ﾞ
    0.62
    ，
    0.61
     on
    0.60
     error
    0.60
    。
    0.60
    Act Density 0.000%

    No Known Activations