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

    Neuronpedia

    INDEX
    Explanations

    polynomials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proactively
    -0.08
     unbearable
    -0.08
     القيام
    -0.08
     interview
    -0.08
    休
    -0.08
    _sleep
    -0.08
     做
    -0.08
     sightseeing
    -0.07
    �
    -0.07
    )、
    -0.07
    POSITIVE LOGITS
     हिस्सा
    0.08
    wang
    0.08
    ystä
    0.08
     coins
    0.08
     symmetry
    0.08
    aget
    0.08
    aged
    0.07
     coefficients
    0.07
     spellen
    0.07
     reversing
    0.07
    Act Density 0.003%

    No Known Activations