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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries, particularly those marked by question marks

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

    Questions ending with a question mark

    np_acts-logits-general · gemini-2.0-flash

    questions asking for factual answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sumoto
    -0.73
     Alu
    -0.69
    oire
    -0.69
    aure
    -0.67
    ais
    -0.67
    gdx
    -0.65
     Rump
    -0.64
    esta
    -0.63
    ا
    -0.62
    matig
    -0.62
    POSITIVE LOGITS
    ?!?
    1.38
    %?
    1.28
    !?
    1.18
     $?
    1.13
    ?"
    1.10
    ؟
    1.09
     ?
    1.08
    ?!
    1.08
    ’?
    1.08
    ?
    1.06
    Act Density 0.141%

    No Known Activations