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

    Neuronpedia

    INDEX
    Explanations

    protected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     приготов
    -0.08
     चिक
    -0.08
     oatmeal
    -0.08
     Sensors
    -0.08
     Annap
    -0.08
     Nih
    -0.08
     eingestellt
    -0.07
     preload
    -0.07
     Tipps
    -0.07
    Rgb
    -0.07
    POSITIVE LOGITS
    protected
    0.09
     forbidden
    0.09
     infringement
    0.09
     protected
    0.09
     infring
    0.08
    Protected
    0.08
     tumb
    0.08
    au
    0.08
     categorical
    0.08
     lawful
    0.08
    Act Density 0.004%

    No Known Activations