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

    Neuronpedia

    INDEX
    Explanations

    most of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preparations
    -0.09
    しょう
    -0.07
     '&'
    -0.07
     kami
    -0.07
    碇
    -0.07
    宝鸡
    -0.07
     typealias
    -0.07
    'eau
    -0.07
    <Box
    -0.07
     söz
    -0.07
    POSITIVE LOGITS
    아버
    0.07
    Ts
    0.07
    mates
    0.06
    Listen
    0.06
    获
    0.06
    (active
    0.06
    滉
    0.06
    住户
    0.06
     å
    0.06
    华东
    0.06
    Act Density 0.051%

    No Known Activations