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

    Neuronpedia

    INDEX
    Explanations

    instances of high numerical values or importance in a dataset

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

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vagy
    -0.26
     diamantes
    -0.26
    Esperamos
    -0.24
     vilja
    -0.24
    kwür
    -0.23
     sæ
    -0.22
    )，
    -0.22
    ⁩
    -0.21
     bolsillos
    -0.21
     kimse
    -0.21
    POSITIVE LOGITS
     surla
    1.00
     disambiguazione
    0.96
    setVerticalGroup
    0.96
    uxxxx
    0.96
    tagHelperRunner
    0.92
    SequentialGroup
    0.89
    WaitGroup
    0.89
     '\\;'
    0.88
    脚注の使い方
    0.86
    httphttps
    0.85
    Act Density 0.014%

    No Known Activations