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

    Neuronpedia

    INDEX
    Explanations

    analysis and exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ONLY
    0.33
    0.32
     actually
    0.29
     eats
    0.29
     չ
    0.29
     blob
    0.29
    لوار
    0.29
     trivially
    0.29
     بۇ
    0.28
     vendu
    0.28
    POSITIVE LOGITS
    探讨
    0.33
     способствует
    0.32
     обеспечивает
    0.30
    у
    0.29
    有助于
    0.29
     Provides
    0.28
    Provides
    0.28
     exploring
    0.28
    ifting
    0.28
     insightful
    0.28
    Act Density 3.094%

    No Known Activations