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

    Neuronpedia

    INDEX
    Explanations

    bet, betekenis, betreft, betaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     エン
    0.42
     Engel
    0.41
     Raz
    0.40
    cole
    0.39
    وا
    0.38
    洋
    0.38
    ঙ্গ
    0.37
     engel
    0.37
    engel
    0.37
    এন
    0.37
    POSITIVE LOGITS
    eken
    0.56
    reed
    0.44
    rekken
    0.44
    AST
    0.43
    unii
    0.42
    eke
    0.41
    rokken
    0.41
    क्कर
    0.39
     Kenn
    0.39
    asta
    0.39
    Act Density 0.001%

    No Known Activations