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

    Neuronpedia

    INDEX
    Explanations

    exercise physiology measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    琢
    -0.08
    👎
    -0.08
    HexString
    -0.07
     evaluate
    -0.07
    ftware
    -0.07
    icaid
    -0.07
    .*
    -0.07
     teen
    -0.07
    mask
    -0.07
    从严治党
    -0.06
    POSITIVE LOGITS
    ">$
    0.07
    硝
    0.06
     waterfall
    0.06
     powered
    0.06
    ấp
    0.06
    ⇚
    0.06
     ....↵↵
    0.06
    友
    0.06
     состоя
    0.06
     rud
    0.06
    Act Density 0.037%

    No Known Activations