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

    Neuronpedia

    INDEX
    Explanations

    humorous, creative, dramatic style

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Man
    0.42
    iotsitewise
    0.41
     Evaluating
    0.40
    ធី
    0.38
     Safety
    0.38
    लाइड
    0.37
     शुद्ध
    0.37
     கடுமையான
    0.37
     Of
    0.36
     организм
    0.36
    POSITIVE LOGITS
     nhất
    0.53
    -
    0.47
    mente
    0.44
     ترین
    0.42
     flair
    0.42
     شي
    0.40
     أو
    0.40
    لي
    0.39
    /
    0.39
    ၇
    0.39
    Act Density 0.343%

    No Known Activations