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

    Neuronpedia

    INDEX
    Explanations

    references to data structures or parameters in code

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

    commands with flags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.68
     مرئيه
    -0.68
    xase
    -0.68
     queſta
    -0.67
     surla
    -0.66
    ConverterFactory
    -0.65
    WriteTagHelper
    -0.65
     <<<<<<<<<<<<<<
    -0.63
    eaway
    -0.62
     joaat
    -0.61
    POSITIVE LOGITS
     and
    0.35
     comigo
    0.31
     Ciebie
    0.29
    处
    0.29
     natten
    0.29
     Suomessa
    0.28
     illustrationer
    0.27
     Suiza
    0.27
     siebie
    0.27
     conmigo
    0.26
    Act Density 0.024%

    No Known Activations