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

    Neuronpedia

    INDEX
    Explanations

    website urls like github.com and github.io

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prüfung
    0.59
    pflicht
    0.56
    aš
    0.56
    ್ಣ
    0.55
     Nación
    0.55
    тна
    0.54
     Schwester
    0.54
    ürn
    0.53
     Arbeits
    0.53
    λί
    0.52
    POSITIVE LOGITS
     of
    0.71
    6
    0.70
    वायु
    0.70
    s
    0.67
    m
    0.66
    7
    0.64
    ों
    0.61
    EXTRA
    0.61
    QUI
    0.59
    Return
    0.59
    Act Density 0.000%

    No Known Activations