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

    Neuronpedia

    INDEX
    Explanations

    instances of line breaks and newline characters in the text

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

    LaTeX math markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.40
    ruitment
    -0.40
    ification
    -0.40
    TokenNameLPAREN
    -0.39
    ips
    -0.39
    igen
    -0.39
    amoja
    -0.37
    elaar
    -0.37
    rix
    -0.36
    anth
    -0.36
    POSITIVE LOGITS
     enfans
    0.65
     مرئيه
    0.58
     Infór
    0.57
    SequentialGroup
    0.54
    complexContent
    0.54
    IndentedString
    0.54
     trône
    0.53
    Cyfarwyddwr
    0.51
     betreft
    0.51
     wuß
    0.51
    Act Density 0.030%

    No Known Activations