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

    Neuronpedia

    INDEX
    Explanations

    Course Goal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chhoti
    0.79
    ين
    0.77
    раў
    0.77
     läng
    0.76
     Mileage
    0.76
     acrylonitrile
    0.75
    lö
    0.74
     tevé
    0.74
    ары
    0.74
    垪
    0.74
    POSITIVE LOGITS
    きました
    0.76
     електро
    0.76
    お金
    0.71
     особи
    0.71
    )"
    0.70
    political
    0.68
     '**
    0.68
    おすすめ
    0.66
    お
    0.66
    <unused2020>
    0.66
    Act Density 0.004%

    No Known Activations