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

    Neuronpedia

    INDEX
    Explanations

    aaa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สงคร
    -0.07
     Weinstein
    -0.07
    现在已经
    -0.07
     Prepared
    -0.07
    퓝
    -0.07
     правитель
    -0.06
    chedulers
    -0.06
    万博
    -0.06
    쑨
    -0.06
     Overlay
    -0.06
    POSITIVE LOGITS
     blooms
    0.08
    FTA
    0.07
     nanny
    0.07
    }".
    0.07
     rides
    0.07
     файл
    0.07
    	use
    0.07
    Prices
    0.07
    opies
    0.07
    abis
    0.07
    Act Density 0.002%

    No Known Activations