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

    Neuronpedia

    INDEX
    Explanations

    URLs and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    בי
    0.49
    क्लेव
    0.45
    mAb
    0.45
    깎
    0.43
    ValueLayout
    0.42
    ಕ್‌
    0.42
    ported
    0.42
    άν
    0.42
    نان
    0.41
    ביע
    0.41
    POSITIVE LOGITS
     Paris
    0.46
    img
    0.44
    ↵↵
    0.43
     Reading
    0.42
     Essay
    0.42
    o
    0.42
     Life
    0.42
     Image
    0.40
     τόσο
    0.40
     essay
    0.39
    Act Density 0.024%

    No Known Activations