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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structural elements used in code

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

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OCCURRED
    -0.50
    DoubleQuotes
    -0.49
     htons
    -0.47
    opr
    -0.46
    writerow
    -0.44
    irection
    -0.44
    sidemargin
    -0.44
    _{[
    -0.43
    Scaler
    -0.43
     wachten
    -0.43
    POSITIVE LOGITS
    ьаж
    0.50
     diagrama
    0.45
     InputDecoration
    0.43
     '\\;'
    0.42
    يكب
    0.40
     initWith
    0.40
    InputTagHelper
    0.38
    initWith
    0.38
     therewith
    0.38
    IUrlHelper
    0.38
    Act Density 0.046%

    No Known Activations