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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ौक
    -0.08
    _five
    -0.07
    records
    -0.06
     Sports
    -0.06
    -analytics
    -0.06
    وج
    -0.06
     Fruit
    -0.06
     twenty
    -0.06
    305
    -0.06
    _corr
    -0.06
    POSITIVE LOGITS
     παν
    0.07
     trata
    0.06
    =logging
    0.06
    �
    0.06
     Παν
    0.06
    ${
    0.06
    白
    0.06
    忍
    0.06
    _TD
    0.06
    스터
    0.06
    Act Density 0.013%

    No Known Activations