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

    Neuronpedia

    INDEX
    Explanations

    the word "come" followed by low activation on nearby words

    oai_token-act-pair · gemini-2.0-flash

    come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orianCalendar
    -0.64
    ölkerung
    -0.63
    ädie
    -0.61
    เข้า
    -0.60
    MLLoader
    -0.57
    LANDS
    -0.57
     CURLOPT
    -0.57
     Masuk
    -0.56
     <=",
    -0.54
     allAfrica
    -0.54
    POSITIVE LOGITS
    omock
    0.49
    dataIndex
    0.47
     nemlig
    0.47
     derece
    0.43
    GOTREF
    0.41
     hasNext
    0.41
     totiž
    0.41
    ntomas
    0.41
     Swartz
    0.41
     včetně
    0.40
    Act Density 1.114%

    No Known Activations