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

    Neuronpedia

    INDEX
    Explanations

    symbols and syntax related to programming or markup languages

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

    code structure or markup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.67
     noDo
    -0.65
    fromnode
    -0.63
    󠁴
    -0.57
    parsedMessage
    -0.56
    msgTypes
    -0.55
    Traducción
    -0.54
    webElementXpaths
    -0.54
    transQ
    -0.52
     OMITBAD
    -0.52
    POSITIVE LOGITS
     similarly
    0.60
     ebenfalls
    0.59
     Vergnügen
    0.59
     likewise
    0.58
    同样
    0.54
     Gegenteil
    0.54
     málaga
    0.53
     Ebenso
    0.52
     dieselbe
    0.52
    同じく
    0.52
    Act Density 0.046%

    No Known Activations