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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vn
    -0.07
     nhi
    -0.07
     wc
    -0.07
     testCase
    -0.07
     iam
    -0.07
     poised
    -0.07
    _up
    -0.07
    科创
    -0.07
     shoppers
    -0.07
     Wimbledon
    -0.07
    POSITIVE LOGITS
    ӂ
    0.09
    tic
    0.07
    ӫ
    0.07
    펶
    0.07
    🚶
    0.07
     moeten
    0.06
    звон
    0.06
    说过
    0.06
    бе
    0.06
    olid
    0.06
    Act Density 0.001%

    No Known Activations