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

    Neuronpedia

    INDEX
    Explanations

    metals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     determ
    -0.07
    eeper
    -0.06
     "/"
    -0.06
    atial
    -0.06
    EVENT
    -0.06
     ),↵
    -0.06
    		
↵		
↵
    -0.06
     rewarded
    -0.06
     кан
    -0.06
     pressed
    -0.06
    POSITIVE LOGITS
     tf
    0.06
    Cog
    0.06
    cadena
    0.06
    goog
    0.06
    Them
    0.06
    UNG
    0.06
     miền
    0.06
     Dre
    0.06
     triển
    0.06
     оскільки
    0.06
    Act Density 0.162%

    No Known Activations