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

    Neuronpedia

    INDEX
    Explanations

    gall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Dense
    -0.07
    vanished
    -0.07
     Beijing
    -0.06
    Apollo
    -0.06
     utilized
    -0.06
    Ingredients
    -0.06
     Jen
    -0.06
     Bilim
    -0.06
    项
    -0.06
    安装
    -0.06
    POSITIVE LOGITS
    /ag
    0.07
    _associ
    0.07
     pageNum
    0.06
    .maxLength
    0.06
    _EXTENDED
    0.06
    ApiOperation
    0.06
     has
    0.06
    援
    0.06
    手机号
    0.06
    anyl
    0.06
    Act Density 0.002%

    No Known Activations