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

    Neuronpedia

    INDEX
    Explanations

    file paths and code references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Verbesserung
    0.43
     кеңсеси
    0.42
     poor
    0.42
    केंसी
    0.41
     זיי
    0.40
     sowas
    0.40
    𒁍
    0.40
    ән
    0.40
     Statistik
    0.39
     verbessern
    0.39
    POSITIVE LOGITS
    *.
    0.64
    README
    0.64
     *.
    0.55
    readme
    0.49
    *,
    0.46
    state
    0.44
    complete
    0.44
    Makefile
    0.44
    *;
    0.43
    *-
    0.43
    Act Density 0.013%

    No Known Activations