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

    Neuronpedia

    INDEX
    Explanations

    domain names and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    1.58
    зю
    1.53
    G
    1.52
    M
    1.45
     dimes
    1.38
    秶
    1.34
     maximizes
    1.34
    ة
    1.34
     وغير
    1.33
    疵
    1.32
    POSITIVE LOGITS
    та
    1.93
    am
    1.91
    ms
    1.90
    te
    1.82
    ations
    1.79
    ments
    1.79
    ir
    1.78
    son
    1.76
    ів
    1.74
    ින්
    1.73
    Act Density 0.061%

    No Known Activations