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

    Neuronpedia

    INDEX
    Explanations

    Books and literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     congest
    -0.08
    ayaran
    -0.08
    ,:,
    -0.08
     freel
    -0.08
     floating
    -0.07
    floating
    -0.07
     للخ
    -0.07
     pembayaran
    -0.07
     transmitting
    -0.07
     oily
    -0.07
    POSITIVE LOGITS
     classroom
    0.10
     Classroom
    0.10
    Wrapper
    0.10
     Wrapper
    0.09
     wrapper
    0.09
     wrappers
    0.09
     мектеп
    0.09
     textbooks
    0.09
    包装
    0.09
     చద
    0.09
    Act Density 0.052%

    No Known Activations