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

    Neuronpedia

    INDEX
    Explanations

    creative or clever solutions to problems

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

    creative ideas and strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consideración
    -0.35
    prefixer
    -0.34
     Auswahl
    -0.33
     StatefulWidget
    -0.30
     confianza
    -0.30
     étrangère
    -0.30
     valmis
    -0.30
     contrario
    -0.30
     Gegenteil
    -0.30
     Betrach
    -0.29
    POSITIVE LOGITS
     ingenious
    0.69
    TintMode
    0.66
    новништво
    0.64
     trick
    0.60
     contextLoads
    0.59
     surla
    0.59
     tricks
    0.58
     propOrder
    0.58
    invention
    0.57
     Trick
    0.57
    Act Density 0.126%

    No Known Activations