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

    Neuronpedia

    INDEX
    Explanations

    price

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ʅ
    -0.07
    蹿
    -0.07
    shire
    -0.07
    彗
    -0.07
    ʏ
    -0.07
    蒂
    -0.07
     winners
    -0.07
     Swiss
    -0.07
    ಶ
    -0.06
    摔倒
    -0.06
    POSITIVE LOGITS
    斧
    0.07
    parts
    0.07
     unbearable
    0.07
     bases
    0.07
     Issue
    0.07
    formedURLException
    0.07
     bắt
    0.06
     lhs
    0.06
     bla
    0.06
    请大家
    0.06
    Act Density 0.015%

    No Known Activations