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

    Neuronpedia

    INDEX
    Explanations

    absolute value math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     following
    -0.08
     Gran
    -0.07
    ని
    -0.07
     Pub
    -0.07
     Grav
    -0.07
     Guido
    -0.07
    ించే
    -0.07
     inoc
    -0.07
    ిష
    -0.07
    hibition
    -0.07
    POSITIVE LOGITS
    regions
    0.10
    Regions
    0.10
    _regions
    0.10
     først
    0.09
     partitions
    0.09
     quadrant
    0.09
     Regions
    0.09
    -routing
    0.09
     switches
    0.09
     separated
    0.08
    Act Density 0.064%

    No Known Activations