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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     undefeated
    -0.07
    idences
    -0.07
    ीब
    -0.06
    EPHIR
    -0.06
    泉
    -0.06
     FD
    -0.06
    pm
    -0.06
     CSA
    -0.06
     Among
    -0.06
    比赛
    -0.06
    POSITIVE LOGITS
    蓝
    0.07
     الج
    0.07
    .add
    0.07
    .black
    0.07
    (abs
    0.07
    _ALL
    0.07
    <p
    0.07
     (%)
    0.07
    .axes
    0.06
     Useful
    0.06
    Act Density 0.109%

    No Known Activations