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

    Neuronpedia

    INDEX
    Explanations

    Mind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sparse
    -0.07
    (factory
    -0.07
    支
    -0.06
    류
    -0.06
    (Str
    -0.06
    .dropdown
    -0.06
    ropped
    -0.06
    (coeffs
    -0.06
    účast
    -0.06
     düğ
    -0.06
    POSITIVE LOGITS
    ?????
    0.06
    berry
    0.06
    IND
    0.06
     CLIENT
    0.06
    Recently
    0.06
    ictor
    0.06
    441
    0.06
     exc
    0.06
    utors
    0.06
    _trace
    0.06
    Act Density 0.000%

    No Known Activations