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

    Neuronpedia

    INDEX
    Explanations

    your capabilities, movie playing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأعمال
    0.59
     Биз
    0.50
     Благо
    0.49
     ידי
    0.48
    észeti
    0.48
     қо
    0.47
    దర్శ
    0.47
     Бы
    0.47
    едера
    0.47
     الأس
    0.47
    POSITIVE LOGITS
    <0x80>
    0.59
    ya
    0.54
    a
    0.54
     };
    0.46
    다
    0.46
     galore
    0.46
    proteins
    0.45
    \
    0.45
     (€
    0.44
     reduces
    0.43
    Act Density 0.001%

    No Known Activations