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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations and specific entities

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

    conversational turn starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connaissances
    -0.32
     knowledge
    -0.32
     Polri
    -0.31
     âges
    -0.31
     Dra
    -0.31
     défauts
    -0.29
     ceremonia
    -0.29
     regalías
    -0.29
     kuto
    -0.29
     défis
    -0.28
    POSITIVE LOGITS
     estekak
    0.87
    SourceChecksum
    0.83
    parsedMessage
    0.79
     Taktlose
    0.79
    хьтан
    0.79
     للمعارف
    0.78
    ScopeManager
    0.77
     насељу
    0.74
    featureID
    0.73
    цездатний
    0.71
    Act Density 0.050%

    No Known Activations