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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    velte
    -0.07
     iCloud
    -0.07
     niche
    -0.06
     mercy
    -0.06
    icolon
    -0.06
     kob
    -0.06
    руч
    -0.06
     Mvc
    -0.06
    ْب
    -0.06
    lew
    -0.06
    POSITIVE LOGITS
    中国
    0.07
    veyor
    0.06
    atitis
    0.06
     resemble
    0.06
    Cent
    0.06
    (before
    0.06
    pcm
    0.06
     投稿
    0.06
    wow
    0.06
    edido
    0.06
    Act Density 0.011%

    No Known Activations