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

    Neuronpedia

    INDEX
    Explanations

    paypa1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $\--
    0.27
     ahuv
    0.27
     ServicePolicy
    0.26
    𒂠
    0.26
    㭜
    0.26
    BlockFit
    0.26
    㑼
    0.26
    鈳
    0.25
    cevam
    0.25
     Конгрегация
    0.25
    POSITIVE LOGITS
    R
    0.35
    0.34
    p
    0.34
    g
    0.34
    n
    0.34
    r
    0.34
    ic
    0.33
    l
    0.33
    ig
    0.33
    h
    0.33
    Act Density 0.046%

    No Known Activations