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

    Neuronpedia

    INDEX
    Explanations

    research institute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    öglichkeiten
    0.78
    <unused257>
    0.76
     શક્ય
    0.71
    confusion
    0.69
    ленно
    0.69
    azem
    0.68
    ಶ್
    0.68
    গল
    0.65
    াদী
    0.62
    ケーション
    0.61
    POSITIVE LOGITS
    ーストラ
    0.75
     Biotechnology
    0.75
    Beauty
    0.73
     Beauty
    0.73
     dances
    0.71
     Virtue
    0.71
     Dances
    0.70
     अनुया
    0.69
     Cin
    0.69
     Rec
    0.68
    Act Density 0.002%

    No Known Activations