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

    Neuronpedia

    INDEX
    Explanations

    good and society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DOT
    -0.07
    _width
    -0.07
    	fd
    -0.06
     VBox
    -0.06
    مت
    -0.06
    .Y
    -0.06
    @",
    -0.06
    _Template
    -0.06
    вати
    -0.06
    ุญ
    -0.06
    POSITIVE LOGITS
    macro
    0.07
     gaping
    0.06
     conocer
    0.06
     пла
    0.06
     beneficial
    0.06
     dejar
    0.06
     inclination
    0.06
     specializing
    0.06
    ств
    0.06
    λογ
    0.06
    Act Density 0.018%

    No Known Activations