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

    Neuronpedia

    INDEX
    Explanations

    publication and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     서
    0.44
     сезон
    0.41
     butter
    0.40
     endExpNow
    0.38
     लाने
    0.37
     Domingo
    0.37
     hagg
    0.37
     Difficulty
    0.37
     demanded
    0.36
     subdue
    0.36
    POSITIVE LOGITS
    features
    0.45
     features
    0.42
    acariy
    0.39
     CPE
    0.39
    öffentlichung
    0.38
    ्मी
    0.38
    enschaft
    0.37
    เท่า
    0.37
    Bengal
    0.37
     عبارت
    0.37
    Act Density 0.000%

    No Known Activations