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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    submitButton
    -0.07
    concat
    -0.06
    surname
    -0.06
    .Rotate
    -0.06
     impacted
    -0.06
     thumbnails
    -0.06
     judging
    -0.06
     remover
    -0.06
     míst
    -0.06
     leadership
    -0.06
    POSITIVE LOGITS
    -am
    0.06
    ΗΤ
    0.06
    arn
    0.06
     |--
    0.06
    athering
    0.06
    reesome
    0.06
    께서
    0.06
    ******/↵
    0.06
     Barnes
    0.06
    |x
    0.06
    Act Density 0.000%

    No Known Activations