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

    Neuronpedia

    INDEX
    Explanations

    strategies related to decision-making and planning

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

    strategy after, chosen to, left out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.63
     الرياضيه
    -0.62
    rungsseite
    -0.61
    Portale
    -0.59
    TargetException
    -0.58
    setVerticalGroup
    -0.57
    ########.
    -0.57
     surla
    -0.57
    WebVitals
    -0.56
    RetentionPolicy
    -0.54
    POSITIVE LOGITS
    hilangan
    0.35
    眼前
    0.32
     Cliquez
    0.31
     Menge
    0.31
    intios
    0.31
     Erst
    0.30
     Explained
    0.30
     Appreciate
    0.29
     appreciated
    0.29
     Geschichten
    0.29
    Act Density 0.127%

    No Known Activations