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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _zero
    -0.08
     licking
    -0.07
     ging
    -0.06
    бав
    -0.06
    _eff
    -0.06
    ebo
    -0.06
     distr
    -0.06
    ัช
    -0.06
     nug
    -0.06
     quar
    -0.06
    POSITIVE LOGITS
    enin
    0.06
    れば
    0.06
     setuptools
    0.06
    ---------------
    0.06
     disregard
    0.06
    Version
    0.06
    (common
    0.06
    clang
    0.06
    一级
    0.06
     홈페이지
    0.06
    Act Density 0.044%

    No Known Activations