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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "first" and other indicators of primary occurrences or introductions

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

    something happening for the "first" or "second" time

    np_acts-logits-general · gemini-2.0-flash

    first time or event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dumne
    -0.43
    Either
    -0.43
     últimas
    -0.43
     behold
    -0.43
    <bos>
    -0.42
     ultimo
    -0.42
    例文帳に追加
    -0.42
    either
    -0.41
    rawdź
    -0.41
     utiles
    -0.41
    POSITIVE LOGITS
     ever
    0.94
    AsUp
    0.86
    __*/
    0.81
    DispatchToProps
    0.81
    archiviato
    0.80
    HomeAsUpEnabled
    0.79
    PerformLayout
    0.78
    httphttps
    0.76
    ever
    0.74
    HasAnnotation
    0.73
    Act Density 0.166%

    No Known Activations