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

    Neuronpedia

    INDEX
    Explanations

    say punctuation after number

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MIN
    -0.08
     MASS
    -0.07
     Two
    -0.07
     Att
    -0.07
     పిల్ల
    -0.07
     PLUS
    -0.07
    (depth
    -0.07
     [
    -0.07
    双
    -0.07
    ERING
    -0.07
    POSITIVE LOGITS
    über
    0.09
    ристи
    0.08
     пользователей
    0.08
    ึ่ง
    0.08
    ӯр
    0.08
     semuanya
    0.08
     երաժ
    0.08
    ibe
    0.08
     ევროპ
    0.08
    يفون
    0.08
    Act Density 0.004%

    No Known Activations