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

    Neuronpedia

    INDEX
    Explanations

    the opening of a document or significant sections that contain intro or summary statements

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

    Follows punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    syntactic structures and markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AsUp
    -0.66
    MemoryWarning
    -0.60
     صوتيه
    -0.59
     fieldNum
    -0.59
    Становништво
    -0.58
    rungsseite
    -0.58
    makeatother
    -0.54
     model
    -0.53
    ########.
    -0.52
     Wikipédia
    -0.52
    POSITIVE LOGITS
    Point
    0.66
     point
    0.58
    point
    0.57
     Point
    0.55
    ArgsConstructor
    0.54
     POINT
    0.53
    EndProject
    0.51
    )':
    0.50
    _));
    0.49
    kontroll
    0.48
    Act Density 0.019%

    No Known Activations