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

    Neuronpedia

    INDEX
    Explanations

    initialize ui or components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    THING
    2.14
    ে
    2.05
    iiv
    1.98
    i
    1.91
    ють
    1.91
    ک
    1.90
    ição
    1.76
    ydı
    1.73
    ческие
    1.70
    ০
    1.68
    POSITIVE LOGITS
    न
    2.14
    ка
    1.97
    ان
    1.76
    ્સ
    1.73
    ー
    1.67
    িন
    1.65
    р
    1.65
    lə
    1.63
    lari
    1.59
    मधील
    1.59
    Act Density 0.001%

    No Known Activations