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

    Neuronpedia

    INDEX
    Explanations

    company names and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Newtonian
    0.41
     contrived
    0.40
     suppuration
    0.39
     shrinkage
    0.38
     retardation
    0.38
     LongNumber
    0.38
     photometric
    0.38
     ২০১০
    0.37
     scanty
    0.37
     испо
    0.37
    POSITIVE LOGITS
     celebrates
    0.61
     LGBTQ
    0.57
     Announces
    0.54
     উদযাপন
    0.50
    TikTok
    0.48
    Biden
    0.48
     Launches
    0.47
    🫶
    0.46
    ChatGPT
    0.46
     telehealth
    0.46
    Act Density 0.000%

    No Known Activations