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

    Neuronpedia

    INDEX
    Explanations

    endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᨄ
    -0.07
    ليك
    -0.06
     purse
    -0.06
    nç
    -0.06
    /arm
    -0.06
     Insider
    -0.06
     Sleep
    -0.06
     Drivers
    -0.06
     Purchase
    -0.06
    Sz
    -0.06
    POSITIVE LOGITS
     DEFIN
    0.08
    חת
    0.07
    全产业链
    0.07
    figcaption
    0.07
    🕷
    0.07
    留下了
    0.07
    宜昌
    0.07
    嗪
    0.07
     stay
    0.07
    九大
    0.07
    Act Density 0.007%

    No Known Activations