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

    Neuronpedia

    INDEX
    Explanations

    ternal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     little
    -0.06
     Rounds
    -0.06
     Marcos
    -0.06
    써
    -0.06
     Lawrence
    -0.06
     polygons
    -0.06
    给
    -0.06
     Wolves
    -0.06
     Midwest
    -0.06
     Fo
    -0.06
    POSITIVE LOGITS
     Eternal
    0.09
     eternal
    0.07
    /qu
    0.07
    /init
    0.07
    ernity
    0.07
     送
    0.07
    _alt
    0.07
    ΗΡ
    0.07
    haul
    0.07
    /is
    0.07
    Act Density 0.002%

    No Known Activations