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

    Neuronpedia

    INDEX
    Explanations

    the word "literature"

    oai_token-act-pair · gemini-2.0-flash

    Literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     webdriver
    -0.75
     Wikimedijinoj
    -0.69
    SPATH
    -0.65
    medriver
    -0.65
    teady
    -0.64
    asantry
    -0.63
    drawal
    -0.63
    CDCl
    -0.62
    ufact
    -0.62
    bolista
    -0.61
    POSITIVE LOGITS
     chrétien
    0.82
     chrétiens
    0.76
     avoient
    0.73
     étoit
    0.72
     épis
    0.71
     étoient
    0.69
     américains
    0.68
     répar
    0.67
     enfans
    0.67
    ="">
    0.66
    Act Density 1.515%

    No Known Activations