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

    Neuronpedia

    INDEX
    Explanations

    Numbers and word lengths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coffee
    -0.06
     decreases
    -0.06
     pressed
    -0.06
    Drink
    -0.06
     Bears
    -0.06
     bearing
    -0.06
     famed
    -0.06
    但
    -0.06
     jokes
    -0.06
    اضر
    -0.06
    POSITIVE LOGITS
    reglo
    0.07
     conven
    0.06
    úc
    0.06
    <Int
    0.06
     자동
    0.06
    αιο
    0.06
     *}↵↵
    0.06
     Mentor
    0.06
    _OPT
    0.06
     список
    0.06
    Act Density 0.020%

    No Known Activations