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

    Neuronpedia

    INDEX
    Explanations

    subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $c
    -0.07
    Christian
    -0.07
    ingleton
    -0.06
    -rounded
    -0.06
    ukes
    -0.06
     car
    -0.06
    .col
    -0.06
     patio
    -0.06
     چرخ
    -0.06
     capitals
    -0.06
    POSITIVE LOGITS
    (router
    0.07
     输出
    0.07
    ��态
    0.07
    .selectAll
    0.06
    .Orientation
    0.06
     되었
    0.06
     outfield
    0.06
    _REC
    0.06
     nội
    0.06
     слу
    0.06
    Act Density 0.011%

    No Known Activations