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

    Neuronpedia

    INDEX
    Explanations

    Discussions involving time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ממוצע
    -0.08
    "}
    -0.07
    .Columns
    -0.07
    时不时
    -0.07
    -)
    -0.07
    _userid
    -0.07
     Anda
    -0.07
     expected
    -0.07
    _mm
    -0.07
    .userid
    -0.07
    POSITIVE LOGITS
     Brothers
    0.07
    .copyWith
    0.06
    imb
    0.06
    조
    0.06
    ayers
    0.06
    �
    0.06
     Miss
    0.06
     Steam
    0.06
     sister
    0.06
    ::::
    0.06
    Act Density 0.134%

    No Known Activations