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

    Neuronpedia

    INDEX
    Explanations

    references to programming code structures or expressions

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

    code print output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьажоргаш
    -0.40
     gynhyrchwyd
    -0.35
    səhifə
    -0.35
     незавершена
    -0.35
     arşivlendi
    -0.32
    パターン
    -0.31
     PeEnEo
    -0.31
    のかも
    -0.31
    farwyddwr
    -0.31
     pattern
    -0.31
    POSITIVE LOGITS
     &___
    0.73
     Monfieur
    0.73
     Jefus
    0.71
     Houſe
    0.63
     purpoſe
    0.63
     pleaſure
    0.62
    TagMode
    0.60
     Chriftian
    0.59
     Chrift
    0.59
     StatelessWidget
    0.56
    Act Density 0.002%

    No Known Activations