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

    Neuronpedia

    INDEX
    Explanations

    structured data terms and programming keywords

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

    technical terms and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.76
     AssemblyCulture
    -0.73
    AnchorStyles
    -0.71
     typelib
    -0.70
     Chwiliwch
    -0.69
    Rüyada
    -0.67
     للاسماء
    -0.66
     Wikiseite
    -0.65
     ujednoznacz
    -0.63
     CreateTagHelper
    -0.63
    POSITIVE LOGITS
    참고
    0.62
    其
    0.44
     Tsai
    0.43
     its
    0.39
     Example
    0.39
     Rat
    0.38
     Cal
    0.38
    ive
    0.38
    cal
    0.38
    CAL
    0.38
    Act Density 0.489%

    No Known Activations