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

    Neuronpedia

    INDEX
    Explanations

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.54
    م
    0.52
    ي
    0.47
     Conan
    0.46
     BIM
    0.45
     Laravel
    0.45
     персонал
    0.43
    ن
    0.43
     SQL
    0.42
     SEO
    0.42
    POSITIVE LOGITS
    NS
    0.45
    ിക്കാം
    0.44
    istro
    0.43
    ijo
    0.43
     its
    0.42
     at
    0.41
    லி
    0.41
    eso
    0.41
     boldly
    0.41
    ಷ್ಣ
    0.41
    Act Density 0.000%

    No Known Activations