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

    Neuronpedia

    INDEX
    Explanations

    None explicitly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fórmulas
    0.41
     машинасы
    0.40
     व्हिडी
    0.40
     automaty
    0.39
     paralysie
    0.38
    ंजनों
    0.38
    лизм
    0.38
    زمت
    0.38
     umożliw
    0.38
    izoph
    0.37
    POSITIVE LOGITS
    ↵↵
    0.58
     অতিরিক্ত
    0.50
     eneste
    0.48
    ה
    0.47
    無い
    0.46
     spade
    0.45
    ↵↵↵↵
    0.45
     crepe
    0.44
     noted
    0.44
     Lichten
    0.43
    Act Density 0.009%

    No Known Activations