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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods, within the text

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

    paid commissions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtand
    -0.47
     themſelves
    -0.38
     néz
    -0.37
     himſelf
    -0.36
     dens
    -0.36
     كومونز
    -0.36
     abstractions
    -0.35
     مشتر
    -0.35
    MIDDLEWARE
    -0.35
     resol
    -0.34
    POSITIVE LOGITS
    AndEndTag
    0.55
    Diweddarwch
    0.51
    ValueStyle
    0.50
    transQ
    0.49
     kasarigan
    0.49
    SharedDtor
    0.49
     jadx
    0.47
    ()][
    0.47
    章节错误
    0.44
    ServletConfig
    0.44
    Act Density 0.001%

    No Known Activations