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

    Neuronpedia

    INDEX
    Explanations

    very, excellent, realistic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.43
    ླ
    0.42
    CacheV
    0.41
    ୃ
    0.40
     préférences
    0.39
     proverb
    0.39
    究竟
    0.38
     semblable
    0.38
     किंवा
    0.38
     ovipares
    0.38
    POSITIVE LOGITS
     There
    0.52
     Tiene
    0.50
     Очень
    0.47
     VERY
    0.44
     tiene
    0.44
     Есть
    0.44
     настоящий
    0.44
     очень
    0.43
     Excellent
    0.43
     EDTA
    0.43
    Act Density 0.076%

    No Known Activations