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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brisk
    -0.07
    Metal
    -0.06
    '][
    -0.06
    압
    -0.06
     Ank
    -0.06
     двух
    -0.06
    ischer
    -0.06
    怪
    -0.06
    dorf
    -0.06
    _SM
    -0.06
    POSITIVE LOGITS
    攝
    0.07
     Bowling
    0.07
     tidak
    0.07
    ↵		
↵
    0.06
    ๆ
    0.06
     ๆ
    0.06
     spray
    0.06
     ngày
    0.06
     squad
    0.06
    
    0.06
    Act Density 0.000%

    No Known Activations