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

    Neuronpedia

    INDEX
    Explanations

    range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蔈
    -0.07
    /licenses
    -0.07
    .Popen
    -0.07
    ⋼
    -0.06
     мет
    -0.06
    .getContentPane
    -0.06
    תוך
    -0.06
    裡面
    -0.06
     doorstep
    -0.06
    퍿
    -0.06
    POSITIVE LOGITS
    .game
    0.08
     LC
    0.08
     Surge
    0.07
    光电
    0.07
    产
    0.07
     rotation
    0.07
     WB
    0.07
    }[
    0.07
    ря
    0.07
     Cp
    0.07
    Act Density 0.083%

    No Known Activations