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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture and media sources

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

    starting user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awarkan
    -0.35
    körper
    -0.33
    ılığı
    -0.33
    anggap
    -0.29
     intercamb
    -0.29
     conmigo
    -0.28
     électroniques
    -0.28
    iertamente
    -0.28
    ționale
    -0.28
    ケーション
    -0.27
    POSITIVE LOGITS
    astify
    0.66
    postsleuth
    0.62
     surla
    0.57
    RenderAtEndOf
    0.57
    ArrowToggle
    0.56
    ChildScrollView
    0.56
    DeleteBehavior
    0.55
    MLLoader
    0.55
    TRIBUN
    0.54
    transQ
    0.53
    Act Density 0.072%

    No Known Activations