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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sign
    -0.06
    นาย
    -0.06
    .getJSONObject
    -0.06
     gemacht
    -0.06
     сек
    -0.06
    ентов
    -0.06
     폐
    -0.06
    :new
    -0.06
    -Americ
    -0.06
     객체
    -0.05
    POSITIVE LOGITS
    asi
    0.07
    history
    0.07
    branches
    0.07
     unsett
    0.07
     hypnot
    0.06
     Denis
    0.06
    John
    0.06
    �
    0.06
    vented
    0.06
    ızı
    0.06
    Act Density 0.048%

    No Known Activations