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

    Neuronpedia

    INDEX
    Explanations

    polynomials and variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psik
    -0.08
     anecd
    -0.08
     workout
    -0.08
    Workout
    -0.07
     troubleshoot
    -0.07
    hab
    -0.07
     jaka
    -0.07
    pisode
    -0.07
     fark
    -0.07
     உட
    -0.07
    POSITIVE LOGITS
     markers
    0.09
    markers
    0.09
    城县
    0.08
     symbols
    0.08
    изацию
    0.08
     unborn
    0.08
     chemicals
    0.08
     biomarkers
    0.08
    .web
    0.08
    (Ljava
    0.08
    Act Density 0.015%

    No Known Activations