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

    Neuronpedia

    INDEX
    Explanations

    "ical" suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鳥
    -0.07
     вся
    -0.07
     *));↵
    -0.06
     jedn
    -0.06
    _hidden
    -0.06
    رض
    -0.06
     就
    -0.06
     graduates
    -0.06
    $info
    -0.06
    勤
    -0.06
    POSITIVE LOGITS
    ounding
    0.08
     enforcing
    0.07
     embroidery
    0.07
     ><
    0.07
     numer
    0.06
     computation
    0.06
     numerical
    0.06
     instruments
    0.06
     advantage
    0.06
    IClient
    0.06
    Act Density 0.002%

    No Known Activations