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

    Neuronpedia

    INDEX
    Explanations

    Document sections, figures, chapters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .exec
    -0.07
    rav
    -0.06
    책
    -0.06
    ­n
    -0.06
    logging
    -0.06
    emoc
    -0.06
    ambio
    -0.06
    YW
    -0.06
    -week
    -0.06
    ulus
    -0.06
    POSITIVE LOGITS
     khám
    0.07
    ослав
    0.07
    Layer
    0.06
    (animated
    0.06
     dig
    0.06
     بشكل
    0.06
    .dy
    0.06
     وغير
    0.06
     एन
    0.06
    ursal
    0.06
    Act Density 0.008%

    No Known Activations