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

    Neuronpedia

    INDEX
    Explanations

    old ways and world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Serial
    0.40
    عيب
    0.40
     приобрета
    0.40
    Sib
    0.39
     innumerable
    0.39
     intric
    0.38
     Serialization
    0.38
    愊
    0.38
     Serial
    0.38
     esemplari
    0.38
    POSITIVE LOGITS
    eta
    0.42
     levers
    0.41
    ޖ
    0.41
    ito
    0.40
    lings
    0.40
    fa
    0.39
    lle
    0.39
    ovac
    0.38
    oting
    0.38
    gning
    0.38
    Act Density 0.004%

    No Known Activations