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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΡΙ
    -0.07
     Meadows
    -0.07
     somewhere
    -0.07
    }}},↵
    -0.06
    398
    -0.06
     propiedad
    -0.06
    \uC
    -0.06
     aussi
    -0.06
     Millet
    -0.06
     wre
    -0.06
    POSITIVE LOGITS
    ГО
    0.07
    _sa
    0.07
    ун
    0.06
     distur
    0.06
    	entry
    0.06
    永
    0.06
    =headers
    0.06
     appellant
    0.06
     blink
    0.05
     коміс
    0.05
    Act Density 0.066%

    No Known Activations