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

    Neuronpedia

    INDEX
    Explanations

    Dates in the 1800s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otherwise
    -0.07
    please
    -0.07
     preliminary
    -0.07
     cuales
    -0.07
     oneself
    -0.06
    (r
    -0.06
    RestController
    -0.06
     tuples
    -0.06
     seus
    -0.06
    _I
    -0.06
    POSITIVE LOGITS
    170
    0.08
    320
    0.08
     Watt
    0.08
    80
    0.07
    330
    0.07
     закуп
    0.07
    160
    0.07
    60
    0.07
    40
    0.07
    510
    0.07
    Act Density 0.321%

    No Known Activations