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

    Neuronpedia

    INDEX
    Explanations

    EU, Igor Levit, account, vast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    此同时
    0.98
    ﺓ
    0.96
    ль
    0.93
    шие
    0.92
    вим
    0.91
    лната
    0.91
    ﺕ
    0.91
    дің
    0.90
    ваме
    0.90
     ondul
    0.89
    POSITIVE LOGITS
    i
    0.94
    p
    0.92
    ap
    0.89
    //
    0.89
    ıyla
    0.86
    ad
    0.85
    r
    0.85
    ../
    0.84
    ara
    0.84
    my
    0.81
    Act Density 0.000%

    No Known Activations