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

    Neuronpedia

    INDEX
    Explanations

    accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shade
    -0.06
    台灣
    -0.06
     Share
    -0.06
     lugar
    -0.06
     longer
    -0.06
    尔
    -0.06
    伤
    -0.06
    ерб
    -0.06
    w
    -0.06
    mpar
    -0.06
    POSITIVE LOGITS
     말이
    0.07
    OCUMENT
    0.07
     LS
    0.07
    Inserted
    0.06
     cread
    0.06
    -my
    0.06
     ход
    0.06
    237
    0.06
    (;
    0.06
    (environment
    0.06
    Act Density 0.008%

    No Known Activations