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

    Neuronpedia

    INDEX
    Explanations

    pageant and solitaire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.91
    ด
    0.77
     that
    0.75
    ों
    0.74
    า
    0.71
    れる
    0.70
     on
    0.69
     jako
    0.66
     curviliné
    0.66
    ร
    0.66
    POSITIVE LOGITS
    c
    0.86
    k
    0.82
     pageant
    0.79
    ج
    0.71
    ни
    0.71
    cett
    0.70
    </strong>
    0.69
    <0x0D>
    0.69
    在
    0.68
    </em>
    0.68
    Act Density 0.001%

    No Known Activations