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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and other symbols, likely to assess document structure

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

    end of sentence transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.47
    AndEndTag
    -0.41
     completeness
    -0.36
    Sinopse
    -0.36
    Viitteet
    -0.36
    DockStyle
    -0.36
    Ligações
    -0.36
    spaceBetween
    -0.35
    étaro
    -0.35
     الحره
    -0.35
    POSITIVE LOGITS
    saraba
    0.56
    sizeCache
    0.50
     ExecuteAsync
    0.49
    paravant
    0.46
    eventually
    0.46
    forChild
    0.44
     řek
    0.43
    **/
    0.41
     eventually
    0.41
     antaranya
    0.40
    Act Density 0.037%

    No Known Activations