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

    Neuronpedia

    INDEX
    Explanations

    mx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fend
    -0.07
    oho
    -0.07
    <Transform
    -0.07
    URED
    -0.07
    _APP
    -0.07
    rops
    -0.07
    SHIP
    -0.07
     SEA
    -0.07
     kindergarten
    -0.07
    processable
    -0.07
    POSITIVE LOGITS
     quận
    0.08
    -us
    0.07
     GLuint
    0.07
    (Return
    0.07
    终于
    0.07
    闵
    0.06
    ús
    0.06
    ヽ
    0.06
    (ns
    0.06
     منذ
    0.06
    Act Density 0.015%

    No Known Activations