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

    Neuronpedia

    INDEX
    Explanations

    standards after specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    2.12
    ي
    1.95
    ம்
    1.80
    ে
    1.77
    써
    1.75
    ه
    1.69
    ीय
    1.67
    aaf
    1.58
    oise
    1.58
    وج
    1.57
    POSITIVE LOGITS
     именно
    1.77
    臾
    1.62
    时候
    1.55
     rispett
    1.53
    ᄍ
    1.53
    ्लो
    1.51
     dagli
    1.44
     tan
    1.42
    bout
    1.42
     Actress
    1.42
    Act Density 0.000%

    No Known Activations