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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لق
    0.51
    نق
    0.49
    ف
    0.48
     (
    0.48
     Kaye
    0.47
    ช
    0.46
    થી
    0.46
    に
    0.45
    精心
    0.45
    FormatException
    0.44
    POSITIVE LOGITS
     세포
    0.56
    ˜</
    0.50
    FileDialog
    0.48
     പേര
    0.46
    readFile
    0.45
    ISSU
    0.45
    newList
    0.44
    തു
    0.44
     வீட்டில்
    0.44
     gluon
    0.44
    Act Density 0.000%

    No Known Activations