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

    Neuronpedia

    INDEX
    Explanations

    logging and cinematic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ঝি
    0.47
    囩
    0.45
    ರನ್ನು
    0.44
    花费
    0.43
     সক্রিয়
    0.43
    रन
    0.43
    essä
    0.42
    rando
    0.42
    aloko
    0.41
    сора
    0.41
    POSITIVE LOGITS
    Insights
    0.52
     astounding
    0.43
     excepcional
    0.43
    CIAL
    0.42
     camion
    0.42
     illus
    0.42
     imprensa
    0.42
     Innoc
    0.41
     massif
    0.41
     infus
    0.41
    Act Density 0.001%

    No Known Activations