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

    Neuronpedia

    INDEX
    Explanations

    signs of conditional logic and programming syntax

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

    instances of the closing brace character and occurrences of the word "in."

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

    code contexts and programming constructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queen
    -0.43
     inv
    -0.40
     konge
    -0.39
    nigh
    -0.38
     credential
    -0.38
     nigh
    -0.37
    OutOf
    -0.37
     setCurrent
    -0.37
     gọn
    -0.36
     elétrica
    -0.35
    POSITIVE LOGITS
     GenerationType
    0.99
     CreateTagHelper
    0.95
    Geplaatst
    0.92
     ویکی‌پدیا
    0.86
    fromnode
    0.84
     MaterialApp
    0.80
    EndContext
    0.80
    BeginContext
    0.78
    +#+
    0.78
    enumi
    0.77
    Act Density 0.025%

    No Known Activations