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

    Neuronpedia

    INDEX
    Explanations

    floating point numbers and math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uken
    0.76
     Cada
    0.72
    列
    0.70
     列
    0.69
     Untersuch
    0.69
     बकरी
    0.68
    kens
    0.68
     przetwarz
    0.68
    یکشن
    0.66
    列
    0.64
    POSITIVE LOGITS
     floating
    1.42
    Overflow
    1.42
     Overflow
    1.41
     math
    1.41
     Floating
    1.40
     rounding
    1.40
     float
    1.38
     overflow
    1.37
    sqrt
    1.37
     sqrt
    1.36
    Act Density 0.617%

    No Known Activations