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

    Neuronpedia

    INDEX
    Explanations

    stereotypical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ot
    0.80
    ER
    0.55
    '
    0.52
     continuamente
    0.48
    </h2>
    0.48
    ので
    0.48
    你
    0.47
     ছিল
    0.46
    ᅢ
    0.46
    art
    0.46
    POSITIVE LOGITS
    ки
    0.90
    ى
    0.88
    ിൽ
    0.82
    ری
    0.82
    ю
    0.74
    ند
    0.71
    and
    0.65
    ць
    0.65
    пу
    0.64
    کس
    0.63
    Act Density 0.525%

    No Known Activations