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

    Neuronpedia

    INDEX
    Explanations

    function definitions and control flow structures in code

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

    Code-related content, such as parentheses or try/catch blocks

    np_acts-logits-general · gemini-2.0-flash

    nothing or {}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.79
    Personendaten
    -0.78
    Tikang
    -0.77
     EconPapers
    -0.74
    IsContent
    -0.72
    بوابة
    -0.71
    zös
    -0.71
    "):
    -0.70
     linkovi
    -0.68
     mergeFrom
    -0.68
    POSITIVE LOGITS
     nothing
    1.23
     Nothing
    1.11
    Nothing
    1.08
     NOTHING
    1.02
    nothing
    1.00
     rien
    0.99
    NOTHING
    0.95
     {}
    0.95
     ничего
    0.84
     noth
    0.81
    Act Density 0.068%

    No Known Activations