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

    Neuronpedia

    INDEX
    Explanations

    Sun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pier
    -0.08
     truncated
    -0.07
    有益
    -0.07
     Outstanding
    -0.07
    到期
    -0.07
    有關
    -0.07
     kapı
    -0.07
     discouraged
    -0.07
     irresistible
    -0.07
     extravagant
    -0.07
    POSITIVE LOGITS
    كو
    0.07
    덴
    0.07
    놔
    0.07
     nhật
    0.07
     Canucks
    0.06
    keys
    0.06
    𬘘
    0.06
    𐌺
    0.06
    هذه
    0.06
    ptide
    0.06
    Act Density 0.005%

    No Known Activations