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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mastered
    -0.07
     bày
    -0.06
     coach
    -0.06
    thing
    -0.06
     Manchester
    -0.06
    started
    -0.06
    لاح
    -0.06
    782
    -0.06
     خودش
    -0.06
     hizmet
    -0.06
    POSITIVE LOGITS
    ательно
    0.07
     ''),
    0.07
    (.
    0.07
    owego
    0.06
    {:
    0.06
    [selected
    0.06
    (cell
    0.06
    나는
    0.06
    _cover
    0.06
    ixer
    0.06
    Act Density 0.001%

    No Known Activations