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

    Neuronpedia

    INDEX
    Explanations

    code structure and formatting elements

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

    closing code blocks and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    енча
    -0.47
     devices
    -0.34
     transfieras
    -0.32
     resources
    -0.31
     painting
    -0.31
     hoarding
    -0.31
    BUCKET
    -0.30
    __/
    -0.29
     wise
    -0.29
     also
    -0.28
    POSITIVE LOGITS
    httphttps
    0.68
    CloseOperation
    0.58
    новниш
    0.58
     HttpNotFound
    0.56
    Tembelea
    0.56
    tagHelperRunner
    0.52
    RepeatedField
    0.52
    LabelTagHelper
    0.52
    FormTagHelper
    0.51
     Италијани
    0.51
    Act Density 0.037%

    No Known Activations