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

    Neuronpedia

    INDEX
    Explanations

    descriptive text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trilogy
    -0.07
     Liberals
    -0.06
     Dip
    -0.06
    ous
    -0.06
    	Q
    -0.06
    906
    -0.06
    .tele
    -0.06
    頃
    -0.06
     ducks
    -0.06
    UGINS
    -0.06
    POSITIVE LOGITS
    (auth
    0.07
    _USAGE
    0.06
     قسم
    0.06
     painfully
    0.06
     xlabel
    0.06
    ازی
    0.06
    )).↵
    0.06
    lico
    0.06
     itemName
    0.06
    ?“↵↵
    0.06
    Act Density 0.019%

    No Known Activations