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

    Neuronpedia

    INDEX
    Explanations

    Logging levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StartTime
    -0.07
    lerle
    -0.06
    Flying
    -0.06
     ethernet
    -0.06
     учрежд
    -0.06
     території
    -0.06
    -0.06
     bac
    -0.06
     triple
    -0.06
     ^{}
    -0.06
    POSITIVE LOGITS
    ibs
    0.07
    �
    0.07
     Juli
    0.06
     cos
    0.06
     Norm
    0.06
    _sent
    0.06
    했습니다
    0.06
    (describing
    0.06
     있음
    0.06
    �
    0.06
    Act Density 0.011%

    No Known Activations