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

    Neuronpedia

    INDEX
    Explanations

    lines, pipes, or cables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    તર
    0.43
     respond
    0.43
     Vér
    0.42
     Zeichen
    0.42
     Blaze
    0.42
    d
    0.42
     exhibited
    0.41
     Pool
    0.41
     Ecke
    0.41
     Rok
    0.41
    POSITIVE LOGITS
    Ȼ
    0.43
    維持
    0.43
    ళ్ళు
    0.41
    和
    0.41
    不像
    0.40
    Ѳ
    0.40
    astian
    0.40
    叓
    0.40
    繁
    0.39
     和
    0.39
    Act Density 0.000%

    No Known Activations