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

    Neuronpedia

    INDEX
    Explanations

    terms related to administrative and regulatory processes

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

    before "has," "was," "is"

    np_acts-logits-general · gemini-2.0-flash

    issues, plants, techniques, tributes, missions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setof
    -0.47
     mergeFrom
    -0.45
    agno
    -0.45
     NSCoder
    -0.44
    Océ
    -0.43
     дописавши
    -0.43
    hams
    -0.43
    жешь
    -0.42
    uxxxx
    -0.42
     Same
    -0.42
    POSITIVE LOGITS
     itself
    1.14
     itſelf
    0.94
    টি
    0.83
    itself
    0.80
    évaluateur
    0.80
     herself
    0.80
     مذ
    0.77
     Itself
    0.75
    ValueStyle
    0.73
     نفسها
    0.72
    Act Density 0.657%

    No Known Activations