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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )")
    1.05
     μαζί
    0.88
    maal
    0.87
    ත්
    0.86
    次に
    0.86
    {{
    0.84
     жало
    0.84
    )$}
    0.83
     parenteral
    0.82
    )}+
    0.82
    POSITIVE LOGITS
    té
    0.80
    ів
    0.78
    imli
    0.78
    িও
    0.77
    那样
    0.76
     eventualmente
    0.76
     (=
    0.76
    िटी
    0.75
    semibold
    0.75
    هَا
    0.74
    Act Density 0.412%

    No Known Activations