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

    Neuronpedia

    INDEX
    Explanations

    punctuations or formatting elements in technical or numerical contexts

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

    Follows abbreviations or initialisms

    np_acts-logits-general · gemini-2.0-flash

    community infrastructure, services, or organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iſt
    -1.36
     myſelf
    -1.31
     Monfieur
    -1.25
    出版年
    -1.23
     ―――――
    -1.21
     pleaſure
    -1.19
     Efq
    -1.19
     Jefus
    -1.19
     purpoſe
    -1.18
     faſt
    -1.17
    POSITIVE LOGITS
    api
    0.47
     De
    0.45
    ...
    0.45
     b
    0.44
    .
    0.43
     Dem
    0.43
    ,
    0.42
     B
    0.41
    ↵↵
    0.41
     
    0.41
    Act Density 0.978%

    No Known Activations