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

    Neuronpedia

    INDEX
    Explanations

    Wi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Undertaker
    -0.59
     Heid
    -0.56
     Alo
    -0.56
     thăng
    -0.54
     Baptists
    -0.53
    utors
    -0.52
    PyExc
    -0.52
     Paglinawan
    -0.51
    IInterface
    -0.51
     Itachi
    -0.51
    POSITIVE LOGITS
     المعيارى
    0.58
     برانيه
    0.51
    NOPQRST
    0.48
    ViewFeatures
    0.48
     encuent
    0.46
    Precis
    0.44
    MemoryWarning
    0.43
    setupUi
    0.43
    FS
    0.42
    FCS
    0.42
    Act Density 0.002%

    No Known Activations