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

    Neuronpedia

    INDEX
    Explanations

    hedging language, or words indicating caution and reservation

    oai_token-act-pair · gemini-2.0-flash

    Legal/cautionary announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dụng
    -0.55
    PRWEB
    -0.55
     Seeder
    -0.54
    Filmografia
    -0.54
    Bibliograf
    -0.54
    veyard
    -0.53
    istoitu
    -0.52
    tvguidetime
    -0.52
     suck
    -0.51
    thargy
    -0.51
    POSITIVE LOGITS
    <bos>
    0.57
    #![
    0.55
     NavController
    0.51
    цездатний
    0.51
    ؤلاء
    0.51
     andererseits
    0.50
     rağmen
    0.50
    tdessen
    0.49
     crainte
    0.49
     moreover
    0.48
    Act Density 1.633%

    No Known Activations