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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bölün
    0.41
     buttocks
    0.40
    bx
    0.39
     ursprüng
    0.39
     restructured
    0.39
    σ
    0.39
     transceiver
    0.38
    ator
    0.38
    ♂
    0.38
    AB
    0.37
    POSITIVE LOGITS
    䔋
    0.43
     인도
    0.42
    峙
    0.41
     Rien
    0.41
    秵
    0.40
    дый
    0.40
     لإ
    0.39
     Throwable
    0.39
    ᅵ
    0.39
    㛲
    0.38
    Act Density 0.001%

    No Known Activations