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

    Neuronpedia

    INDEX
    Explanations

    Windows API calls with Ex suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Soci
    0.40
    orys
    0.38
     Saeed
    0.37
    lifer
    0.36
    abel
    0.36
     Patrick
    0.36
    iction
    0.35
     Nathaniel
    0.35
     tub
    0.35
     NT
    0.35
    POSITIVE LOGITS
    Ex
    0.69
     Ex
    0.56
     екс
    0.52
    ex
    0.49
    EX
    0.48
     ex
    0.48
    W
    0.45
     exif
    0.43
     экс
    0.42
    Ｗ
    0.42
    Act Density 0.016%

    No Known Activations