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

    Neuronpedia

    INDEX
    Explanations

    ync

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озвращает
    -0.07
    (report
    -0.07
     Vk
    -0.06
    contrib
    -0.06
    -nav
    -0.06
    _hook
    -0.06
     travail
    -0.06
    comput
    -0.06
    �
    -0.06
    ,length
    -0.06
    POSITIVE LOGITS
     более
    0.07
     detrimental
    0.06
    .life
    0.06
    _THAN
    0.06
     underst
    0.06
     athleticism
    0.06
    Hero
    0.06
     northern
    0.06
     motorists
    0.06
     eBay
    0.06
    Act Density 0.002%

    No Known Activations