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

    Neuronpedia

    INDEX
    Explanations

    items or entities, typically in the context of a list or categorization

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

    Tokens after abbreviations/initials

    np_acts-logits-general · gemini-2.0-flash

    country codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    -0.67
     não
    -0.61
     doesn
    -0.59
     nicht
    -0.58
     не
    -0.57
     tidak
    -0.53
     de
    -0.53
     didn
    -0.52
     isn
    -0.52
     niet
    -0.52
    POSITIVE LOGITS
     ModelExpression
    1.10
    Personensuche
    1.10
     raiſ
    1.07
     Efq
    1.06
     Monfieur
    1.05
    NameInMap
    1.03
     itſelf
    1.01
     Theſe
    1.00
    OGND
    0.99
     nakalista
    0.99
    Act Density 0.072%

    No Known Activations