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
     Colo
    -0.07
    XAxis
    -0.07
    -mediated
    -0.07
    enzel
    -0.07
     Steiner
    -0.07
     Kana
    -0.07
    റെ
    -0.07
    sty
    -0.07
    .trade
    -0.07
     divulg
    -0.07
    POSITIVE LOGITS
    338
    0.08
     */,↵
    0.07
    जब
    0.07
     ND
    0.07
     whale
    0.07
     ']
    0.07
     Sm
    0.07
    390
    0.07
    _without
    0.07
     Trit
    0.07
    Act Density 0.006%

    No Known Activations