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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or strong emotions

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

    Follows punctuation or interjections

    np_acts-logits-general · gemini-2.0-flash

    punctuation and positive sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.93
     initComponents
    -0.72
    encodeWith
    -0.70
    MessageOf
    -0.68
     unknownFields
    -0.67
    AndEndTag
    -0.62
    })()
    -0.61
     "..\..\..\
    -0.61
    )*/
    -0.60
    parsedMessage
    -0.60
    POSITIVE LOGITS
     Hmmm
    0.65
     perfect
    0.63
    ็จ
    0.61
     good
    0.59
     pretty
    0.59
    Nice
    0.58
     nice
    0.58
     great
    0.55
    good
    0.55
     modelAndView
    0.54
    Act Density 0.205%

    No Known Activations