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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     statistical
    -0.07
     zag
    -0.07
     among
    -0.07
    發揮
    -0.06
     vastly
    -0.06
    nan
    -0.06
    ask
    -0.06
    八
    -0.06
     topped
    -0.06
     ô
    -0.06
    POSITIVE LOGITS
    /modules
    0.07
    分子
    0.07
     época
    0.07
    итель
    0.06
     עליו
    0.06
     fluor
    0.06
    _FACTORY
    0.06
    トイレ
    0.06
    דמי
    0.06
    .Media
    0.06
    Act Density 0.005%

    No Known Activations