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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks separating clauses or items in a list

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

    non-English and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RODUZIONE
    -0.36
    towym
    -0.35
    chon
    -0.35
     Fehl
    -0.34
    аз
    -0.34
    IUrlHelper
    -0.34
     челове
    -0.34
     history
    -0.33
     folosit
    -0.33
     human
    -0.33
    POSITIVE LOGITS
    featureID
    0.52
    localctx
    0.48
     gynhyrchwyd
    0.46
    astéroïdes
    0.46
    \{\\
    0.45
    󠁿
    0.44
    Билгалдахарш
    0.43
     Cerebral
    0.42
     كومونز
    0.42
    HomeAsUpEnabled
    0.42
    Act Density 0.002%

    No Known Activations