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

    Neuronpedia

    INDEX
    Explanations

    real name, truly random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.19
    یم
    1.91
     Бе
    1.84
    Бе
    1.84
    ه
    1.73
    ים
    1.72
    ्स
    1.71
    )،
    1.66
    ς
    1.65
    ல்
    1.64
    POSITIVE LOGITS
    IST
    1.61
    р
    1.61
    诰
    1.59
    benar
    1.59
    teste
    1.55
    politik
    1.55
    blooded
    1.55
    จริง
    1.53
    痹
    1.52
    nosed
    1.51
    Act Density 0.710%

    No Known Activations