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

    Neuronpedia

    INDEX
    Explanations

    opening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    停车位
    -0.07
     때
    -0.07
    盛世
    -0.07
    Screen
    -0.06
    另一半
    -0.06
     when
    -0.06
     absentee
    -0.06
     detergent
    -0.06
     cub
    -0.06
     fears
    -0.06
    POSITIVE LOGITS
     milano
    0.07
    fon
    0.07
     Tup
    0.07
     remix
    0.07
     """
    0.07
    造
    0.07
     '''
    0.07
    _encoded
    0.07
    mage
    0.06
    patterns
    0.06
    Act Density 0.053%

    No Known Activations