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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue or quotations in the text

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

    opening quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bibinfo
    -0.60
    rboles
    -0.51
    BibitemShut
    -0.50
    pecabe
    -0.49
    genodigd
    -0.49
     stanovnika
    -0.49
    Semoga
    -0.48
     miniaturka
    -0.48
     nahilalakip
    -0.48
     ainfi
    -0.48
    POSITIVE LOGITS
    SequentialGroup
    0.50
    httphttps
    0.46
    <bos>
    0.44
     ModelExpression
    0.41
    BASELINE
    0.38
    isContained
    0.35
    "
    0.35
    typeorm
    0.34
     吋
    0.34
    ngdoc
    0.33
    Act Density 0.011%

    No Known Activations