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

    Neuronpedia

    INDEX
    Explanations

    Type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     استان
    -0.08
     PO
    -0.07
     }),
    -0.07
    zeń
    -0.06
     Мари
    -0.06
    _forward
    -0.06
     센
    -0.06
    centre
    -0.06
    _Generic
    -0.06
     Are
    -0.06
    POSITIVE LOGITS
    见
    0.07
    绿
    0.07
    >↵↵↵
    0.07
     Dodd
    0.06
     bolt
    0.06
    /image
    0.06
     liebe
    0.06
    /org
    0.06
    quelle
    0.06
     dejting
    0.06
    Act Density 0.000%

    No Known Activations