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

    Neuronpedia

    INDEX
    Explanations

    **

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deficits
    -0.08
     />↵
    -0.07
     mantener
    -0.07
    ｜
    -0.07
     �
    -0.07
    -minded
    -0.06
    352
    -0.06
     Yorkers
    -0.06
    identify
    -0.06
     MMM
    -0.06
    POSITIVE LOGITS
     форм
    0.06
     joker
    0.06
    Sync
    0.06
    Solution
    0.06
    KER
    0.06
     administrator
    0.06
    RATE
    0.06
     reperc
    0.06
    _scenario
    0.06
    lev
    0.06
    Act Density 0.002%

    No Known Activations