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

    Neuronpedia

    INDEX
    Explanations

    =>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    英文
    -0.07
    个国家
    -0.07
    URE
    -0.07
    ون
    -0.07
     udp
    -0.07
    ripp
    -0.06
    更新
    -0.06
     Option
    -0.06
     Sutton
    -0.06
     FAILURE
    -0.06
    POSITIVE LOGITS
     __("
    0.07
     stimulating
    0.07
    都喜欢
    0.07
    ’am
    0.06
     interp
    0.06
    来到了
    0.06
    חז
    0.06
    ﺳ
    0.06
    ilos
    0.06
    Recording
    0.06
    Act Density 0.004%

    No Known Activations