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

    Neuronpedia

    INDEX
    Explanations

    syntax related to code structure and closing brackets

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

    JSON, XML, HTML structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.71
     виправивши
    -0.69
    principalTable
    -0.66
    addContainerGap
    -0.65
    ArgumentParser
    -0.60
    DoubleQuotes
    -0.56
    دانشنامهٔ
    -0.54
    setColumns
    -0.54
    ParallelGroup
    -0.52
     Roskov
    -0.51
    POSITIVE LOGITS
    帖最后由
    0.38
     dirait
    0.35
    Amicalement
    0.34
    └──
    0.33
    uride
    0.33
    loit
    0.33
    abbix
    0.32
     enfans
    0.32
     kasarigan
    0.32
    olingo
    0.31
    Act Density 0.042%

    No Known Activations