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

    Neuronpedia

    INDEX
    Explanations

    number 6 followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いた
    0.78
    性
    0.65
    )."
    0.64
    tedir
    0.64
    SCOPE
    0.63
    ள்ளது
    0.63
    ารย์
    0.63
    ).”
    0.62
    графии
    0.61
    ammation
    0.61
    POSITIVE LOGITS
    k
    0.95
    m
    0.89
    ার
    0.85
    обще
    0.75
    piry
    0.75
    cambrian
    0.75
    g
    0.75
    cknowled
    0.74
    kopf
    0.74
    t
    0.74
    Act Density 0.365%

    No Known Activations