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

    Neuronpedia

    INDEX
    Explanations

    specific medical or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ن
    0.52
     activate
    0.45
    身份证
    0.45
     relaunch
    0.44
    范
    0.44
     readline
    0.44
    马
    0.43
    endio
    0.42
     Clos
    0.42
    n
    0.41
    POSITIVE LOGITS
    ၂
    0.56
     သ
    0.55
    ків
    0.54
    िस्थित
    0.50
     美術
    0.50
    ២
    0.49
     cholera
    0.47
     ଏ
    0.47
    ө
    0.47
    AsyncKeyState
    0.46
    Act Density 0.000%

    No Known Activations