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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors and expressions of admiration

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

    positive superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    клопе
    -0.51
     schéma
    -0.41
    แก่
    -0.41
     auroit
    -0.39
     évit
    -0.39
     témoin
    -0.38
     typo
    -0.38
     دیکھیے
    -0.38
    Bureau
    -0.37
     utilisateur
    -0.37
    POSITIVE LOGITS
    printStackTrace
    0.59
    AndEndTag
    0.57
     ModelExpression
    0.54
     amazing
    0.53
    ftagPool
    0.52
     EconPapers
    0.49
    ContentAsync
    0.49
    Incredible
    0.47
     AMAZING
    0.47
    setVerticalGroup
    0.47
    Act Density 0.009%

    No Known Activations