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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting markers in the text

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

    document structure separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.77
    pecabe
    -0.63
    httphttps
    -0.63
    Schicken
    -0.62
    netinet
    -0.59
    Джерела
    -0.59
    +#+#
    -0.59
    ientras
    -0.57
    Бележки
    -0.57
     nakalista
    -0.57
    POSITIVE LOGITS
    MIND
    0.33
     fant
    0.32
    Descripció
    0.30
     rhestr
    0.30
    InputTagHelper
    0.29
    crest
    0.28
    mind
    0.28
     MIND
    0.27
    봇
    0.27
    Rhestr
    0.26
    Act Density 0.007%

    No Known Activations