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

    Neuronpedia

    INDEX
    Explanations

    terms related to success and achievement

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

    winning and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quiera
    -0.35
     lecz
    -0.34
     asamblea
    -0.33
     przewod
    -0.31
    berdayakan
    -0.31
     extinción
    -0.31
    |'\
    -0.31
     planea
    -0.31
    LElement
    -0.31
     Strukturen
    -0.31
    POSITIVE LOGITS
     thumbs
    0.68
    +#+
    0.60
     favorably
    0.60
     good
    0.57
     favorable
    0.56
     kudos
    0.55
     positives
    0.54
     bezeichneter
    0.54
    urlpatterns
    0.53
    SuppressMessage
    0.53
    Act Density 0.016%

    No Known Activations