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

    Neuronpedia

    INDEX
    Explanations

    code snippets related to data type manipulation and comparisons

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

    numeric types and bitwise operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.57
    +#+#
    -0.47
     aDecoder
    -0.42
    AsUp
    -0.40
     incons
    -0.38
     Bioaccumulative
    -0.38
    šče
    -0.38
     ért
    -0.38
    šča
    -0.38
     despe
    -0.37
    POSITIVE LOGITS
     CreateTagHelper
    0.52
     <>",
    0.48
    MigrationBuilder
    0.45
     Infórmanos
    0.44
     religione
    0.40
     argint
    0.39
    تقاوى
    0.39
    Selfer
    0.39
    canestro
    0.38
    exitRule
    0.38
    Act Density 0.310%

    No Known Activations