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

    Neuronpedia

    INDEX
    Explanations

    integer types and numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mother
    0.40
    Wend
    0.39
    uffed
    0.39
     mẹ
    0.38
    ICKEL
    0.38
     gand
    0.37
     خۆ
    0.37
    pace
    0.36
     vost
    0.36
    arella
    0.35
    POSITIVE LOGITS
    setcounter
    0.62
     Número
    0.48
    BibitemShut
    0.47
     எண்ணிக்கை
    0.47
    numericUpDown
    0.46
     numbering
    0.46
    Max
    0.46
    enumi
    0.45
     NUMBER
    0.44
    numero
    0.44
    Act Density 0.001%

    No Known Activations