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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lim
    -0.07
    كومة
    -0.07
     악
    -0.07
     yoktur
    -0.07
    μά
    -0.06
    blocks
    -0.06
     imposition
    -0.06
    etur
    -0.06
     travail
    -0.06
    icator
    -0.06
    POSITIVE LOGITS
     #↵
    0.07
     ;;
    0.07
    {}",
    0.07
    I
    0.06
    _MAGIC
    0.06
     PI
    0.06
    nie
    0.06
     Bear
    0.06
     terör
    0.06
    (max
    0.06
    Act Density 0.004%

    No Known Activations