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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue indicators

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

    adjectives and nouns following quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.59
     HasFactory
    -0.42
    impresa
    -0.42
    webElementXpaths
    -0.41
    bleven
    -0.40
    ніципалі
    -0.40
    Demografie
    -0.38
    -0.38
     što
    -0.38
    Sklici
    -0.38
    POSITIVE LOGITS
    存于互联网档案馆
    0.58
    ⤒
    0.56
    tvguidetime
    0.52
    addGap
    0.51
    moral
    0.50
     الحره
    0.49
    tagHelperRunner
    0.49
    entially
    0.45
     CreateTagHelper
    0.45
    prom
    0.44
    Act Density 0.047%

    No Known Activations