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

    Neuronpedia

    INDEX
    Explanations

    say excuse

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reordered
    -0.07
    _Test
    -0.06
    pa
    -0.06
    ику
    -0.06
    arcy
    -0.06
     minded
    -0.06
     frosting
    -0.06
     titled
    -0.06
    -cont
    -0.06
    (end
    -0.06
    POSITIVE LOGITS
    ]):↵
    0.07
     یاد
    0.07
    :"↵
    0.06
     mHandler
    0.06
     shutter
    0.06
    	len
    0.06
    *******/↵↵
    0.06
    %)↵
    0.06
     notion
    0.06
     Searching
    0.06
    Act Density 0.130%

    No Known Activations