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

    Neuronpedia

    INDEX
    Explanations

    use of colloquial language and expressions

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

    Japanese sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.75
    intios
    -0.66
    transQ
    -0.61
     ſoll
    -0.59
     ſondern
    -0.59
     盗撮
    -0.59
    -0.59
    iſche
    -0.57
     Geſch
    -0.57
    niſſe
    -0.57
    POSITIVE LOGITS
    EndContext
    0.33
    exitRule
    0.29
    AddWithValue
    0.29
    墨
    0.29
    shadowOffset
    0.28
    MigrationBuilder
    0.27
     собе
    0.27
     kaarangay
    0.27
     monumento
    0.26
    UnusedPrivate
    0.25
    Act Density 0.037%

    No Known Activations