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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of the word "the" in various contexts

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

    the same or first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁢
    -0.75
    -------
    -0.67
    بوابة
    -0.66
    IContainer
    -0.61
     Roskov
    -0.60
    ContentAsync
    -0.60
    Tembelea
    -0.59
    Diweddarwch
    -0.59
    AndEndTag
    -0.58
    linspace
    -0.58
    POSITIVE LOGITS
     является
    0.39
    ='';
    0.35
     responsible
    0.34
     are
    0.33
    isSame
    0.32
     ganze
    0.31
     являются
    0.30
     явля
    0.30
     same
    0.30
    вля
    0.30
    Act Density 0.099%

    No Known Activations