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

    Neuronpedia

    INDEX
    Explanations

    Headlines and titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yor
    -0.07
     trải
    -0.06
    _prepare
    -0.06
     distrust
    -0.06
    Nous
    -0.06
    istik
    -0.06
     листь
    -0.06
    malıdır
    -0.06
    arks
    -0.06
    원을
    -0.06
    POSITIVE LOGITS
    Posts
    0.07
    cheduling
    0.07
     compens
    0.06
    -edit
    0.06
     Moines
    0.06
     Plate
    0.06
    0.06
     concurrency
    0.06
    BASH
    0.06
    Series
    0.06
    Act Density 0.004%

    No Known Activations