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

    Neuronpedia

    INDEX
    Explanations

    variables and error handling phrases in code

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

    function/method parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.74
    queryInterface
    -0.56
    addGap
    -0.54
    Autoritní
    -0.51
     autorytatywna
    -0.49
    OGND
    -0.49
    ########.
    -0.48
     betweenstory
    -0.47
     gabbana
    -0.45
     Paglinawan
    -0.44
    POSITIVE LOGITS
     again
    0.60
     Again
    0.49
     szint
    0.46
     ebenfalls
    0.46
    again
    0.45
     likewise
    0.45
    Again
    0.44
    これも
    0.44
    PONSE
    0.42
    visiae
    0.41
    Act Density 0.022%

    No Known Activations