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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    സും
    0.45
    زيد
    0.44
    았습니다
    0.40
     ხოლო
    0.39
    ികളും
    0.38
    neas
    0.38
    とのこと
    0.38
    leyebilirsiniz
    0.38
    ilded
    0.37
    했고
    0.37
    POSITIVE LOGITS
    0.37
     AVERAGE
    0.36
    UBS
    0.36
    FR
    0.35
    UR
    0.35
    ITY
    0.34
     dbc
    0.34
    :'.
    0.34
    洋
    0.34
    ψ
    0.34
    Act Density 0.178%

    No Known Activations