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

    Neuronpedia

    INDEX
    Explanations

    say ". word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Leon
    -0.08
    .jackson
    -0.07
     Хо
    -0.07
    关心
    -0.07
     QWidget
    -0.07
    中国
    -0.07
     champions
    -0.07
     Bhar
    -0.06
     Colombia
    -0.06
    Australia
    -0.06
    POSITIVE LOGITS
     curve
    0.07
     {↵↵↵↵
    0.07
    serialized
    0.06
    新政
    0.06
    persons
    0.06
    _Service
    0.06
    vis
    0.06
     pantry
    0.06
    .getWindow
    0.06
    swer
    0.06
    Act Density 0.006%

    No Known Activations