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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peuvent
    -0.07
    =t
    -0.07
     �
    -0.07
     vlád
    -0.07
     std
    -0.07
     ventilation
    -0.07
     helper
    -0.07
     tackles
    -0.07
     terminals
    -0.07
    ISMATCH
    -0.07
    POSITIVE LOGITS
    지도
    0.06
    Notify
    0.06
    ilmek
    0.06
    �
    0.06
    �
    0.06
     plunge
    0.06
    ัช
    0.06
    invisible
    0.05
    現在
    0.05
    보내기
    0.05
    Act Density 0.001%

    No Known Activations