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

    Neuronpedia

    INDEX
    Explanations

    lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    戬
    0.41
     Farb
    0.40
     Ameri
    0.39
     Cog
    0.38
     Jord
    0.38
    ॉइड
    0.38
    㪇
    0.38
    יין
    0.38
     मिलता
    0.37
     मिलते
    0.37
    POSITIVE LOGITS
    Us
    0.41
    無線
    0.38
    Pe
    0.36
    an
    0.36
    epsilon
    0.36
    計画
    0.36
    _-
    0.35
    公園
    0.35
    antib
    0.35
     mem
    0.35
    Act Density 0.000%

    No Known Activations