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

    Neuronpedia

    INDEX
    Explanations

    about constantly evolving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    По
    0.48
    ハイ
    0.47
    стон
    0.47
     Подо
    0.46
    рной
    0.46
    と一緒に
    0.45
    ここ
    0.45
     dispersed
    0.45
     Walton
    0.44
    кер
    0.43
    POSITIVE LOGITS
     רבים
    0.46
     pv
    0.45
     hordes
    0.44
     pesticides
    0.42
     অন্তত
    0.42
     leagues
    0.41
     словами
    0.41
    elijkheid
    0.40
     eBooks
    0.40
     dv
    0.40
    Act Density 0.001%

    No Known Activations