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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation, specifically commas

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

    code structure and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‬‬
    -0.40
     Kết
    -0.38
     kæ
    -0.38
     Вікі
    -0.38
    fscanf
    -0.37
     these
    -0.37
     NEG
    -0.37
    mont
    -0.37
     ezt
    -0.36
     acti
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.52
     ,
    0.51
    saraba
    0.50
     [,
    0.47
    }(),
    0.47
    SharedCtor
    0.46
    fromnode
    0.46
    [,
    0.45
     {,
    0.45
    ├──
    0.45
    Act Density 0.030%

    No Known Activations