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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax or elements within code

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

    user prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lhes
    -0.38
     passagem
    -0.33
      
    -0.31
    łóż
    -0.31
     Genehmigung
    -0.31
     lay
    -0.29
     the
    -0.29
     thiếu
    -0.28
     olev
    -0.28
     acı
    -0.28
    POSITIVE LOGITS
     queſta
    0.89
     Wikimedijinoj
    0.82
     estekak
    0.78
    сылкі
    0.74
     pinulongan
    0.73
    IUrlHelper
    0.72
    TagMode
    0.71
    تقاوى
    0.71
     Италијани
    0.70
    onAttach
    0.70
    Act Density 0.003%

    No Known Activations