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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sept
    -0.08
    emen
    -0.08
     getModel
    -0.07
    Areas
    -0.07
    _open
    -0.07
     Government
    -0.07
     Sext
    -0.07
     Maple
    -0.07
    قد
    -0.07
    _oct
    -0.07
    POSITIVE LOGITS
    娌
    0.07
    ActionButton
    0.07
    漂
    0.07
    虮
    0.07
    $password
    0.06
    体现出
    0.06
    觉得自己
    0.06
    חומרים
    0.06
     lashes
    0.06
    兒
    0.06
    Act Density 0.916%

    No Known Activations