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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    deen
    -0.06
    厂
    -0.06
     bom
    -0.06
    esson
    -0.06
    arth
    -0.06
     ου
    -0.06
    aleur
    -0.06
    _portfolio
    -0.06
     mujer
    -0.06
     ROI
    -0.06
    POSITIVE LOGITS
    .tem
    0.06
     nationalism
    0.06
    环境
    0.06
    =format
    0.06
    ')),↵
    0.06
     дії
    0.06
    PRI
    0.06
    子は
    0.06
     enlight
    0.06
     migli
    0.06
    Act Density 0.034%

    No Known Activations