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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and legal documents

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himo
    -0.59
    rizona
    -0.56
    pherals
    -0.56
     Baillargeon
    -0.55
    NEZ
    -0.54
     nahilalakip
    -0.51
     Endless
    -0.50
    initComponents
    -0.50
    〢
    -0.50
     ẞ
    -0.49
    POSITIVE LOGITS
    __":
    0.60
    __':
    0.57
     betweenstory
    0.50
    AnchorTagHelper
    0.49
    ents
    0.49
    外部リンク
    0.49
    ImageContext
    0.48
     hon
    0.47
    TagMode
    0.47
    MessageTagHelper
    0.46
    Act Density 0.026%

    No Known Activations