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

    Neuronpedia

    INDEX
    Explanations

    sparse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burning
    -0.08
     CL
    -0.07
     lotion
    -0.07
    advertisement
    -0.07
     membrane
    -0.07
     Laser
    -0.07
    (L
    -0.07
    labels
    -0.07
    look
    -0.07
    ujet
    -0.07
    POSITIVE LOGITS
     sparse
    0.11
    sparse
    0.08
    _sparse
    0.08
    Sparse
    0.08
     Sparse
    0.07
    _short
    0.06
     ern
    0.06
    arsity
    0.06
    shi
    0.06
     prone
    0.06
    Act Density 0.002%

    No Known Activations