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

    Neuronpedia

    INDEX
    Explanations

    need information or time series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    世代
    0.45
    spacePad
    0.41
    長
    0.41
    を発
    0.41
     sorpre
    0.40
     Herzen
    0.40
     Grec
    0.40
     contraband
    0.40
    の発
    0.40
     occidental
    0.39
    POSITIVE LOGITS
    Instance
    0.49
    b
    0.48
    Ur
    0.47
    urar
    0.45
    n
    0.45
    f
    0.45
    akili
    0.45
    aceutical
    0.44
     मंदिरा
    0.44
    SSL
    0.44
    Act Density 0.004%

    No Known Activations