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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ac
    -0.08
     Meth
    -0.08
    washing
    -0.08
     commissioned
    -0.08
     Francis
    -0.07
     methane
    -0.07
     compassionate
    -0.07
    meth
    -0.07
    emers
    -0.07
    commission
    -0.07
    POSITIVE LOGITS
     adot
    0.08
     initializer
    0.08
     verändert
    0.08
     sendiri
    0.08
     dijo
    0.08
    _initializer
    0.08
     genomen
    0.08
     solitary
    0.08
     desfr
    0.07
     પડશે
    0.07
    Act Density 0.018%

    No Known Activations