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

    Neuronpedia

    INDEX
    Explanations

    cons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    руд
    -0.07
     Disability
    -0.06
    िजल
    -0.06
    Shows
    -0.06
    ्रम
    -0.06
     خدا
    -0.06
    齐
    -0.06
    جان
    -0.06
    alsex
    -0.06
    764
    -0.06
    POSITIVE LOGITS
    enerating
    0.07
     markup
    0.07
    .dependencies
    0.06
     aberr
    0.06
     extensions
    0.06
    ctions
    0.06
    ATED
    0.06
     poorly
    0.06
    /lib
    0.06
    .mon
    0.06
    Act Density 0.001%

    No Known Activations