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

    Neuronpedia

    INDEX
    Explanations

    Committee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     підприєм
    -0.06
     Nga
    -0.06
     functools
    -0.06
     jin
    -0.06
     arrests
    -0.06
    _xor
    -0.06
     suspected
    -0.06
    ﻠ
    -0.06
     ls
    -0.06
    验证码
    -0.06
    POSITIVE LOGITS
    aras
    0.07
     banks
    0.07
     exercise
    0.07
     specializes
    0.06
     hospitality
    0.06
     Tür
    0.06
    .ad
    0.06
    aleza
    0.06
     bench
    0.06
    .us
    0.06
    Act Density 0.001%

    No Known Activations