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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cell
    -0.07
    หลด
    -0.07
    專
    -0.06
    (ch
    -0.06
    etheless
    -0.06
    雅
    -0.06
     ATK
    -0.06
    迪
    -0.06
    Recorder
    -0.06
    畫
    -0.06
    POSITIVE LOGITS
     "-//
    0.07
     />,
    0.07
    _prior
    0.06
    ()['
    0.06
     Abram
    0.06
     بنابراین
    0.06
     zeroes
    0.06
    ='#
    0.06
     roleId
    0.06
     çift
    0.06
    Act Density 0.058%

    No Known Activations