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

    Neuronpedia

    INDEX
    Explanations

    textbook recommendations (or books)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OU
    -0.07
    angian
    -0.07
     sprintf
    -0.07
     खास
    -0.07
     `/
    -0.07
    ioned
    -0.07
     matt
    -0.06
    оти
    -0.06
     PROD
    -0.06
    -0.06
    POSITIVE LOGITS
    queline
    0.10
    λλη
    0.09
    MBA
    0.08
     MBA
    0.08
     beslut
    0.08
     clueless
    0.08
    liners
    0.08
     mandatario
    0.08
     خاک
    0.08
     Beginners
    0.08
    Act Density 0.005%
    No Known Activations