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

    Neuronpedia

    INDEX
    Explanations

    unchanged

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TextField
    -0.08
     angles
    -0.08
    [][
    -0.07
    ynomials
    -0.07
    create
    -0.07
    国の
    -0.07
    ('/')
    -0.07
     Certain
    -0.06
    rang
    -0.06
    称
    -0.06
    POSITIVE LOGITS
    	do
    0.06
    ERING
    0.06
    وان
    0.06
     BMP
    0.06
    _Category
    0.06
     Mahm
    0.06
     uplifting
    0.06
     Liberation
    0.05
    のだ
    0.05
    (Unit
    0.05
    Act Density 0.013%

    No Known Activations