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

    Neuronpedia

    INDEX
    Explanations

    various types of quotation marks and delimiters

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

    display: block/none; cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proyec
    -0.52
    NameInMap
    -0.50
    ۪
    -0.47
     herum
    -0.47
     laikā
    -0.44
    енча
    -0.43
    tactos
    -0.42
     excès
    -0.42
    Bigr
    -0.42
     ejerc
    -0.41
    POSITIVE LOGITS
    setViewName
    0.65
    addGap
    0.50
     "..\..\..\
    0.49
    SBATCH
    0.48
    VersionUID
    0.48
     "
    0.42
    最快更新
    0.40
     "','
    0.40
     "..\..\
    0.40
    !("
    0.40
    Act Density 0.002%

    No Known Activations