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

    Neuronpedia

    INDEX
    Explanations

    base64 decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     କରି
    0.29
    alupe
    0.29
     MILLER
    0.29
     ಹಾಗ
    0.29
    禣
    0.29
     därför
    0.28
    HILL
    0.28
     dakkh
    0.28
     ܡ
    0.27
    URCH
    0.27
    POSITIVE LOGITS
    ↵
    0.35
    "
    0.30
    begin
    0.29
    .
    0.29
    es
    0.28
     yra
    0.28
     sayısı
    0.28
    @
    0.28
    ન
    0.28
    ی
    0.27
    Act Density 0.015%

    No Known Activations