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

    Neuronpedia

    INDEX
    Explanations

    circles with cx attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    1.15
    ер
    1.02
    ра
    0.91
    ，
    0.91
    ет
    0.86
    、
    0.83
    ก
    0.82
    ası
    0.79
    daki
    0.79
    он
    0.75
    POSITIVE LOGITS
    </em>
    0.89
    </strong>
    0.84
    </sub>
    0.73
    Message
    0.71
    RGB
    0.71
    פה
    0.71
    Additional
    0.70
    Display
    0.70
    </u>
    0.70
    </h2>
    0.69
    Act Density 0.005%

    No Known Activations