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

    Neuronpedia

    INDEX
    Explanations

    references to structural components and performance metrics in various contexts

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

    exceeds expectations and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
    UserScript
    -0.65
     lenker
    -0.63
     ligiloj
    -0.57
    tagHelperRunner
    -0.55
     للمعارف
    -0.54
     Italijani
    -0.53
    Geplaatst
    -0.53
    IBOutlet
    -0.52
    GOTREF
    -0.52
    POSITIVE LOGITS
     exceeded
    0.48
     surpassed
    0.46
     exceed
    0.45
    Життєпис
    0.43
     surpass
    0.40
     surpassing
    0.39
     beyond
    0.36
     exceeding
    0.35
    Override
    0.35
    を超
    0.34
    Act Density 0.094%

    No Known Activations