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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pré
    0.45
     파인더
    0.44
     Петро
    0.44
    াহিয়া
    0.44
    ِمض
    0.43
     травня
    0.43
    havi
    0.43
    나라
    0.42
    瓠
    0.42
    氅
    0.42
    POSITIVE LOGITS
    ↵
    0.55
    az
    0.44
    d
    0.43
    g
    0.42
    z
    0.42
    p
    0.41
    ocument
    0.40
    ینده
    0.40
    r
    0.39
    ing
    0.39
    Act Density 0.007%

    No Known Activations