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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific keywords or terms related to topics of interest

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

    Text followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    discussing members and fans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.73
    énario
    -0.72
     المعيارى
    -0.70
    sätzlich
    -0.70
    roek
    -0.65
     geldt
    -0.62
    ########.
    -0.61
     Allociné
    -0.60
    TokenNameLBRACE
    -0.59
     inderdaad
    -0.59
    POSITIVE LOGITS
     discuss
    1.04
     discusses
    1.03
     talk
    0.82
     discussing
    0.79
     Discuss
    0.79
    discus
    0.77
    Discuss
    0.77
     Discus
    0.77
     explores
    0.73
    Discus
    0.72
    Act Density 0.192%

    No Known Activations