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

    Neuronpedia

    INDEX
    Explanations

    such scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ag
    1.46
     Pp
    1.29
    eners
    1.28
    ah
    1.25
    ee
    1.14
    РЕ
    1.11
     покупки
    1.09
    am
    1.07
    ших
    1.06
    at
    1.05
    POSITIVE LOGITS
     וכ
    1.30
    า
    1.29
    ı
    1.27
    ED
    1.26
    ৫
    1.23
     식으로
    1.20
    い
    1.20
    к
    1.17
    𝘦
    1.15
    一来
    1.14
    Act Density 0.175%

    No Known Activations