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

    Neuronpedia

    INDEX
    Explanations

    class registration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dub
    -0.07
    .transforms
    -0.07
     Amy
    -0.07
     Helpers
    -0.07
     Helper
    -0.07
     Ethics
    -0.06
     evoke
    -0.06
     shopper
    -0.06
     condiciones
    -0.06
    DonaldTrump
    -0.06
    POSITIVE LOGITS
     προϊ
    0.07
    	AT
    0.07
    IMAGE
    0.06
     çerç
    0.06
    .getM
    0.06
    rtle
    0.06
     //================================================================
    0.06
     cuộc
    0.05
     SEX
    0.05
     everlasting
    0.05
    Act Density 0.010%

    No Known Activations