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

    Neuronpedia

    INDEX
    Explanations

    speak

    np_max-act · gemini-2.0-flash

    the mentions of “speaker” or related presentation terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     process
    -0.07
     propriet
    -0.06
     hunting
    -0.06
     프로
    -0.06
     patch
    -0.06
     unfit
    -0.06
    ляют
    -0.06
    .plus
    -0.06
     после
    -0.06
     počtu
    -0.06
    POSITIVE LOGITS
     speaker
    0.09
    Created
    0.07
     Speaker
    0.07
    speaker
    0.07
    بور
    0.07
    721
    0.06
     speakers
    0.06
    342
    0.06
    .liferay
    0.06
     giảng
    0.06
    Act Density 0.018%

    No Known Activations