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

    Neuronpedia

    INDEX
    Explanations

    breakdown with explanations and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    1.12
    ↵
    1.12
     atau
    1.05
     أو
    1.05
     или
    1.03
     ou
    0.97
    或
    0.96
    or
    0.95
     یا
    0.95
     किंवा
    0.93
    POSITIVE LOGITS
     different
    0.99
     informative
    0.88
     각각
    0.87
     impactful
    0.85
     maximized
    0.83
    的主要
    0.83
    levels
    0.81
     maximum
    0.81
    你需要
    0.80
     разных
    0.80
    Act Density 0.726%

    No Known Activations