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

    Neuronpedia

    INDEX
    Explanations

    data scaling/standardization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cake
    -0.07
     Prints
    -0.06
     autres
    -0.06
     Acres
    -0.06
    Controls
    -0.06
    Routine
    -0.06
    backend
    -0.06
     Gar
    -0.06
     fois
    -0.06
    ове
    -0.06
    POSITIVE LOGITS
     exploiting
    0.07
    頼
    0.06
     ostream
    0.06
     Heading
    0.06
    .wikipedia
    0.06
    ocommerce
    0.06
     verbal
    0.06
    apanese
    0.06
     Alleg
    0.06
    (Object
    0.06
    Act Density 0.010%

    No Known Activations