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

    Neuronpedia

    INDEX
    Explanations

    .Module

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     输
    -0.09
     Earth's
    -0.08
     സർക്ക
    -0.07
    र्च
    -0.07
    遥
    -0.07
    क्कर
    -0.07
    benzisa
    -0.07
     земля
    -0.07
    court
    -0.07
    ्यास
    -0.07
    POSITIVE LOGITS
     distributed
    0.09
     ভাবে
    0.08
     SON
    0.08
    distributed
    0.08
    ()?
    0.08
    No
    0.07
    {},
    0.07
     nood
    0.07
    ভাবে
    0.07
    Distributed
    0.07
    Act Density 0.001%

    No Known Activations