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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     introductions
    -0.08
    인은
    -0.07
     ildə
    -0.07
     Availability
    -0.07
     Speakers
    -0.07
     prohibition
    -0.07
     tilgjeng
    -0.07
     œuvres
    -0.07
     terapeut
    -0.07
     alterações
    -0.07
    POSITIVE LOGITS
    s
    0.09
    (path
    0.08
     (${
    0.08
    ѕ
    0.08
    hidr
    0.08
    agger
    0.08
     Faktor
    0.08
     காவ
    0.07
    factor
    0.07
    voerder
    0.07
    Act Density 0.075%

    No Known Activations