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

    Neuronpedia

    INDEX
    Explanations

    complaining/negative comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ization
    -0.08
    ized
    -0.07
     Noon
    -0.07
     arti
    -0.07
     adip
    -0.07
     inférieur
    -0.07
    eris
    -0.07
     �
    -0.07
     važ
    -0.07
     Diagram
    -0.07
    POSITIVE LOGITS
     contradict
    0.10
     आरोप
    0.10
     aço
    0.09
     contradictory
    0.09
     ആരോപ
    0.09
    кімет
    0.09
     विपक्ष
    0.09
     विवाद
    0.09
     respectful
    0.09
     ಆರೋಪ
    0.09
    Act Density 0.121%

    No Known Activations