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

    Neuronpedia

    INDEX
    Explanations

    mock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ensional
    -0.08
     Supplement
    -0.07
     dadurch
    -0.07
     Remodeling
    -0.07
     याद
    -0.07
    christ
    -0.07
     हुई
    -0.07
     યાદ
    -0.07
     artificially
    -0.07
     Episodes
    -0.07
    POSITIVE LOGITS
     Danny
    0.08
     ESTA
    0.07
    Stripe
    0.07
     lump
    0.07
    .Mock
    0.07
    ес
    0.07
    開催
    0.07
     تف
    0.07
     ment
    0.07
     spirited
    0.07
    Act Density 0.004%

    No Known Activations