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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with the effectiveness or functionality of tasks or solutions

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

    "works" and its positive effects/adjectives

    np_acts-logits-general · gemini-2.0-flash

    works well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InvalidProtocol
    -0.74
     otomatig
    -0.74
    RenderAtEndOf
    -0.73
    dafx
    -0.70
     فريبيس
    -0.68
    URLException
    -0.68
    InjectAttribute
    -0.67
     <=",
    -0.66
    ttino
    -0.63
     nahilalakip
    -0.61
    POSITIVE LOGITS
     wonders
    0.91
     fine
    0.71
     magic
    0.70
     miracles
    0.69
     magique
    0.63
     against
    0.61
     Wonders
    0.61
     magically
    0.61
     best
    0.61
     wonder
    0.59
    Act Density 0.088%

    No Known Activations