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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _MODULES
    -0.08
    liament
    -0.07
    мещ
    -0.07
    _overlay
    -0.07
    .timezone
    -0.07
     мы
    -0.07
     krit
    -0.07
    раж
    -0.07
    شة
    -0.06
    ント
    -0.06
    POSITIVE LOGITS
     "\\"
    0.07
    örper
    0.06
    .ix
    0.06
    START
    0.06
     automatically
    0.06
    .AWS
    0.06
    858
    0.06
     hdf
    0.05
     getch
    0.05
     Basel
    0.05
    Act Density 0.000%

    No Known Activations