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

    Neuronpedia

    INDEX
    Explanations

    Java programming language keywords and class imports

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

    Code, imports, and math symbols

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.41
    waitKey
    -0.40
    новниш
    -0.39
    发表于
    -0.38
    ValueStyle
    -0.31
    FunctionFlags
    -0.30
    ByType
    -0.28
    diğini
    -0.28
     باسم
    -0.27
    wapV
    -0.26
    POSITIVE LOGITS
    Datuak
    0.69
    Autoritní
    0.59
    SequentialGroup
    0.59
    [@BOS@]
    0.57
     referenties
    0.57
    <unused41>
    0.57
    <unused43>
    0.57
    <unused28>
    0.57
    <unused8>
    0.57
    <unused23>
    0.57
    Act Density 0.128%

    No Known Activations