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

    Neuronpedia

    INDEX
    Explanations

    text/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ılıyor
    -0.06
     scooter
    -0.06
    шую
    -0.06
    sov
    -0.06
     Yani
    -0.06
     Transformation
    -0.06
    \Command
    -0.06
    .groups
    -0.06
    مو
    -0.06
    ittest
    -0.06
    POSITIVE LOGITS
     Leicester
    0.07
    Biz
    0.07
    (bb
    0.06
    International
    0.06
     Win
    0.06
     bj
    0.06
     lain
    0.06
     Treat
    0.06
     points
    0.06
     mineral
    0.06
    Act Density 0.000%

    No Known Activations