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

    Neuronpedia

    INDEX
    Explanations

    ag followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aggressive
    0.49
     omen
    0.44
     slit
    0.44
     aggressively
    0.42
     sweat
    0.40
     adv
    0.39
     tearing
    0.39
    ABET
    0.38
     dimensions
    0.38
     targeting
    0.38
    POSITIVE LOGITS
    Plastic
    0.43
     Hemen
    0.43
    hubungan
    0.42
    াহিয়া
    0.42
    ColorScheme
    0.41
     क्विंट
    0.40
     وګټ
    0.40
    fohlen
    0.40
    Pinned
    0.40
    𒋾
    0.40
    Act Density 0.003%

    No Known Activations