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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "The" at the start of a line

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     The
    -0.66
     continuant
    -0.50
    kapital
    -0.46
    DropTable
    -0.45
     THE
    -0.45
    الصفحه
    -0.44
    yta
    -0.44
    λαν
    -0.44
     ISTAT
    -0.43
     Wolken
    -0.43
    POSITIVE LOGITS
    <bos>
    2.16
    /*
    0.68
    /**
    0.64
     itſelf
    0.62
    //
    0.60
    '}>
    0.57
     neceff
    0.57
     estekak
    0.55
    #!/
    0.53
    IsContent
    0.53
    Act Density 0.484%

    No Known Activations