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

    Neuronpedia

    INDEX
    Explanations

    question marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있는데
    -0.06
     bounds
    -0.06
     данны
    -0.06
     chặt
    -0.06
     fare
    -0.06
     classes
    -0.06
    는데
    -0.06
    нє
    -0.06
     WEIGHT
    -0.06
     президент
    -0.06
    POSITIVE LOGITS
    _OID
    0.06
    (stdout
    0.06
    heim
    0.06
     Serve
    0.06
    ,output
    0.06
    렉
    0.06
     ')
    0.06
     �
    0.06
    lectic
    0.06
    )."
    0.06
    Act Density 0.054%

    No Known Activations