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

    Neuronpedia

    INDEX
    Explanations

    web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RNG
    -0.07
    iances
    -0.07
     Salmon
    -0.06
     FORCE
    -0.06
    ueling
    -0.06
    З
    -0.06
    -s
    -0.06
    odb
    -0.06
    距離
    -0.06
     lst
    -0.06
    POSITIVE LOGITS
     rau
    0.07
     gerek
    0.07
    諸
    0.07
     ZX
    0.06
    ısıyla
    0.06
     Italy
    0.06
    					↵
    0.06
     Už
    0.06
     kå
    0.06
     trochu
    0.06
    Act Density 0.117%

    No Known Activations