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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     loss
    -0.07
    XL
    -0.07
    venues
    -0.07
    uhl
    -0.07
    طر
    -0.07
     Health
    -0.07
    _Data
    -0.07
    中信
    -0.07
    نصف
    -0.07
     saves
    -0.07
    POSITIVE LOGITS
     bears
    0.07
    .obtain
    0.07
    "struct
    0.07
     Tencent
    0.07
     enthus
    0.07
    iseum
    0.07
    .Predicate
    0.07
     phi
    0.07
     ję
    0.07
    urrect
    0.07
    Act Density 0.005%

    No Known Activations