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

    Neuronpedia

    INDEX
    Explanations

    attribute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     показ
    -0.06
     HB
    -0.06
     zahrn
    -0.06
    doctrine
    -0.06
    ua
    -0.06
     arbitr
    -0.06
    Pow
    -0.06
     piston
    -0.06
     pups
    -0.05
     noble
    -0.05
    POSITIVE LOGITS
    Cipher
    0.08
    (""
    0.07
     й
    0.06
    ierrez
    0.06
    umeric
    0.06
    	cout
    0.06
     casually
    0.06
    éru
    0.06
     behaviours
    0.06
    _driver
    0.06
    Act Density 0.051%

    No Known Activations