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

    Neuronpedia

    INDEX
    Explanations

    down fill, jacket, feathers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UNIX
    0.66
     Communic
    0.66
     așa
    0.66
     आदिवासी
    0.64
     RCLCPP
    0.64
     K
    0.63
     POST
    0.62
     HOW
    0.62
     Kommun
    0.62
     KISS
    0.61
    POSITIVE LOGITS
    ;
    0.87
    -
    0.78
    یم
    0.66
    "
    0.64
    는
    0.63
    –
    0.62
    &(
    0.61
    &
    0.60
    at
    0.59
     down
    0.59
    Act Density 0.000%

    No Known Activations