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

    Neuronpedia

    INDEX
    Explanations

    bumping into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.90
    ﺭ
    0.85
    </h2>
    0.84
    ون
    0.84
    </h3>
    0.82
    ut
    0.79
    </strong>
    0.75
     a
    0.74
    هم
    0.73
    ע
    0.72
    POSITIVE LOGITS
    くちゃ
    0.85
    au
    0.81
    ளில்
    0.80
    dürü
    0.77
     bumping
    0.76
    ד
    0.75
    től
    0.72
    ዃ
    0.72
    otricha
    0.71
    uć
    0.71
    Act Density 0.001%

    No Known Activations