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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     professors
    -0.07
     Ли
    -0.07
     airing
    -0.07
    韩
    -0.07
     cez
    -0.07
     Fare
    -0.07
     Received
    -0.06
     comparisons
    -0.06
     PUB
    -0.06
    ————————————————
    -0.06
    POSITIVE LOGITS
     �
    0.06
     ข
    0.06
    otch
    0.06
    ...">↵
    0.06
     objedn
    0.06
    setError
    0.06
    									↵
    0.06
    	lua
    0.06
    upertino
    0.06
    üçük
    0.06
    Act Density 0.071%

    No Known Activations