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

    Neuronpedia

    INDEX
    Explanations

    statistics and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     süt
    -0.07
     millionaire
    -0.07
     yani
    -0.06
     meilleurs
    -0.06
    ónico
    -0.06
     André
    -0.06
    ,params
    -0.06
     publishers
    -0.06
     Providers
    -0.06
     shirt
    -0.06
    POSITIVE LOGITS
    вад
    0.07
    idak
    0.06
     О
    0.06
    (real
    0.06
     hugely
    0.06
     astounding
    0.06
    (-
    0.06
     devastation
    0.06
    ，以及
    0.06
    люч
    0.06
    Act Density 0.011%

    No Known Activations