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

    Neuronpedia

    INDEX
    Explanations

    summarize text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hatu
    0.83
    曌
    0.83
     അമേ
    0.83
    sted
    0.82
    disciplinary
    0.82
     fulfils
    0.81
    祯
    0.81
    旿
    0.81
     ऑफिशियल
    0.80
    sina
    0.80
    POSITIVE LOGITS
     Conclusions
    0.84
    情节
    0.75
     Caffeine
    0.74
     Extracts
    0.74
    歸
    0.73
    ிரா
    0.72
     Events
    0.71
    ரை
    0.70
    EventType
    0.70
    Events
    0.69
    Act Density 0.133%

    No Known Activations