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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,response
    -0.07
     whiteColor
    -0.07
    —or
    -0.06
    /remove
    -0.06
    rep
    -0.06
    _el
    -0.06
     tác
    -0.06
    ,url
    -0.06
    ，就
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     میلیون
    0.06
    948
    0.06
    ポイント
    0.06
    名無しさん
    0.06
    划
    0.06
    rak
    0.06
    多少
    0.06
    Translated
    0.06
    ersive
    0.06
    mpjes
    0.06
    Act Density 0.045%

    No Known Activations