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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    باقي
    -0.08
    anuts
    -0.07
    phony
    -0.07
    éments
    -0.07
    颛
    -0.06
     Stap
    -0.06
     Northwestern
    -0.06
    pageNum
    -0.06
    ucci
    -0.06
    برنامج
    -0.06
    POSITIVE LOGITS
    出动
    0.08
    运
    0.07
     ави
    0.07
    ";
    0.07
     الإرهاب
    0.07
     identity
    0.07
     Plot
    0.07
    有效
    0.07
     الحال
    0.07
     effect
    0.07
    Act Density 0.001%

    No Known Activations