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

    Neuronpedia

    INDEX
    Explanations

    noise-cancelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    本文
    -0.08
     memorable
    -0.08
     বিব
    -0.07
     portant
    -0.07
    962
    -0.07
     sized
    -0.07
     hexadecimal
    -0.07
     amphib
    -0.07
     equipe
    -0.07
     tät
    -0.07
    POSITIVE LOGITS
     Cancellation
    0.11
     suppression
    0.10
     mitigation
    0.10
    ancellation
    0.10
     cancelling
    0.10
     cancellation
    0.10
    Cancellation
    0.09
     headphones
    0.09
     suppress
    0.09
    (cancel
    0.09
    Act Density 0.004%

    No Known Activations