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

    Neuronpedia

    INDEX
    Explanations

    exit commands and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ą
    2.13
     وعلى
    2.03
    ı
    2.03
    na
    1.91
    ی
    1.87
    0
    1.79
    ことなく
    1.77
    iamo
    1.77
     Anschließend
    1.74
    ا
    1.74
    POSITIVE LOGITS
    ২
    1.71
    ার
    1.66
    icuous
    1.66
     spate
    1.64
     paler
    1.60
     oov
    1.57
    IFIC
    1.56
     abroad
    1.52
    VEY
    1.52
    년
    1.52
    Act Density 0.084%

    No Known Activations