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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific formatting, particularly around dialogue or quotations

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

    Text following titles or headings

    np_acts-logits-general · gemini-2.0-flash

    discussing or about titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wiegend
    -0.60
     sometimes
    -0.58
    mostly
    -0.57
     fometimes
    -0.55
     Tuttavia
    -0.54
     BUT
    -0.53
    тім
    -0.53
    onViewCreated
    -0.52
     mostly
    -0.52
     tetapi
    -0.51
    POSITIVE LOGITS
    Commenting
    0.96
     commented
    0.76
    ###
    0.67
     commenting
    0.67
     Comment
    0.66
    Acerca
    0.65
    ABOUT
    0.64
    QUOTES
    0.63
    About
    0.61
     congratulated
    0.60
    Act Density 0.086%

    No Known Activations