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

    Neuronpedia

    INDEX
    Explanations

    prohibiting sexually suggestive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bern
    0.40
    찰
    0.39
    ŗ
    0.39
    òria
    0.37
    Embedded
    0.37
    لس
    0.36
    Hiking
    0.36
    Transcription
    0.36
    Hospital
    0.36
     Алексе
    0.36
    POSITIVE LOGITS
     outrageous
    0.45
     folly
    0.41
     soz
    0.40
     lunatic
    0.40
     insanity
    0.39
     malign
    0.38
     bridges
    0.38
     Tutti
    0.38
     vàng
    0.38
     fous
    0.38
    Act Density 0.010%

    No Known Activations