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

    Neuronpedia

    INDEX
    Explanations

    Math Symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ffm
    -0.07
    faf
    -0.07
     bran
    -0.07
    ，便
    -0.07
    يكي
    -0.07
     PlayerPrefs
    -0.07
    علومات
    -0.06
    zelf
    -0.06
    -light
    -0.06
    hů
    -0.06
    POSITIVE LOGITS
    ENSIONS
    0.06
     ओर
    0.06
    IM
    0.06
     McGill
    0.05
    _COMPAT
    0.05
    imat
    0.05
    (fn
    0.05
     ART
    0.05
    Warning
    0.05
    anti
    0.05
    Act Density 0.012%

    No Known Activations