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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handles
    -0.08
     прич
    -0.07
     afin
    -0.06
     그냥
    -0.06
    ?“
    -0.06
     клі
    -0.06
     showModal
    -0.06
    wendung
    -0.06
    隐藏
    -0.06
    Anth
    -0.06
    POSITIVE LOGITS
    LER
    0.07
    Morning
    0.07
     murdered
    0.06
     peppers
    0.06
    solve
    0.06
     celebrities
    0.06
    WISE
    0.06
     declined
    0.06
     BOARD
    0.06
     MATLAB
    0.06
    Act Density 0.033%

    No Known Activations