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

    Neuronpedia

    INDEX
    Explanations

    Medical terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fellow
    -0.07
     Ge
    -0.06
     Stress
    -0.06
    ere
    -0.06
     英语
    -0.06
    Water
    -0.06
     bible
    -0.06
    Tomorrow
    -0.06
     потрібно
    -0.06
     بالأ
    -0.06
    POSITIVE LOGITS
     رق
    0.07
     Öl
    0.07
     cung
    0.07
     حو
    0.07
     Colombia
    0.06
    寒
    0.06
     HARD
    0.06
     lông
    0.06
     lack
    0.06
     mantle
    0.06
    Act Density 0.015%

    No Known Activations