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

    Neuronpedia

    INDEX
    Explanations

    references to specific sources or documentation

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

    origin or perspective after from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dirait
    -0.46
    enumi
    -0.45
    querySelector
    -0.44
    ưỡi
    -0.40
     Públicas
    -0.40
    uxxxx
    -0.39
    Lähteet
    -0.37
    oury
    -0.37
    errHandler
    -0.37
    }{*}{
    -0.37
    POSITIVE LOGITS
     from
    0.57
    verwijspagina
    0.57
    FROM
    0.54
     utafitiHapana
    0.51
     throughout
    0.49
     FROM
    0.49
     From
    0.48
    from
    0.48
     vanaf
    0.48
    Dès
    0.45
    Act Density 0.090%

    No Known Activations