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

    Neuronpedia

    INDEX
    Explanations

    code structure and output formatting functions

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

    Code snippets appending to strings

    np_acts-logits-general · gemini-2.0-flash

    code serialization and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.58
    <eos>
    -0.50
    BoxShadow
    -0.50
    دانشنامهٔ
    -0.49
     Paglinawan
    -0.48
    passes
    -0.46
    IVEREF
    -0.45
     vermelhas
    -0.45
     dương
    -0.45
    PropertyGroup
    -0.44
    POSITIVE LOGITS
    évaluateur
    0.77
     forState
    0.75
    يميديا
    0.72
     للمعارف
    0.66
     Италијани
    0.62
    tagHelperRunner
    0.59
    setVerticalGroup
    0.57
     متعلقه
    0.56
    ...”
    0.56
     **/
    0.55
    Act Density 0.205%

    No Known Activations