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

    Neuronpedia

    INDEX
    Explanations

    declarative statements expressing personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    informal constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mektedir
    -0.46
    openSession
    -0.39
    maktadır
    -0.39
    了一口气
    -0.34
    melidir
    -0.33
     orgánico
    -0.33
     hiér
    -0.33
    幸いです
    -0.32
    rrggbb
    -0.32
     gelangen
    -0.32
    POSITIVE LOGITS
     outta
    0.72
    şört
    0.59
    +#+
    0.59
     հղումներ
    0.59
     sorta
    0.58
     بيها
    0.57
     Efq
    0.57
     kinda
    0.57
     Aussie
    0.56
     GONNA
    0.56
    Act Density 0.247%

    No Known Activations