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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hypotheses
    -0.06
     kinds
    -0.06
    δί
    -0.06
    generator
    -0.06
    뷰
    -0.06
    OTA
    -0.06
    fecha
    -0.06
     neod
    -0.06
     wise
    -0.06
     mutlu
    -0.06
    POSITIVE LOGITS
     dissatisfaction
    0.07
     ارتف
    0.07
    groundColor
    0.06
     يم
    0.06
    ็กชาย
    0.06
     Intellectual
    0.06
    ows
    0.06
    根本
    0.06
     Strategy
    0.06
    learn
    0.06
    Act Density 0.027%

    No Known Activations