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

    Neuronpedia

    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash

    This neuron fires on document metadata lines—particularly the author and title fields.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .....↵↵
    -0.07
     menace
    -0.07
    іту
    -0.07
     stopwords
    -0.07
    ("-");↵
    -0.07
    ñas
    -0.06
    											↵
    -0.06
     cola
    -0.06
    =[]↵
    -0.06
    DMA
    -0.06
    POSITIVE LOGITS
    /ng
    0.07
    PING
    0.07
    apache
    0.07
     gerekli
    0.06
    getBytes
    0.06
     Hugo
    0.06
    <vector
    0.06
    AINER
    0.06
    adi
    0.06
    _move
    0.06
    Act Density 0.001%

    No Known Activations