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

    Neuronpedia

    INDEX
    Explanations

    $n$ or subscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayutt
    0.29
    罅
    0.29
    acaktır
    0.29
     ночь
    0.29
     городской
    0.29
    arası
    0.28
    墘
    0.28
    ギフト
    0.28
    㜖
    0.28
    鉚
    0.28
    POSITIVE LOGITS
     T
    0.33
    f
    0.33
     k
    0.32
     F
    0.32
     K
    0.31
    S
    0.31
    _
    0.31
     C
    0.31
     P
    0.31
     is
    0.31
    Act Density 0.141%

    No Known Activations