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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mariners
    -0.06
     Mundo
    -0.06
    asks
    -0.06
    ј
    -0.06
     Flex
    -0.06
     запах
    -0.06
    <Address
    -0.06
     Yüz
    -0.06
     Atlanta
    -0.06
    .LastName
    -0.06
    POSITIVE LOGITS
    /community
    0.07
    剣
    0.07
    implements
    0.07
     तन
    0.07
     hdf
    0.06
     robert
    0.06
    fieldname
    0.06
    '''↵↵
    0.06
    _FIELD
    0.06
    ###############################################################################↵
    0.06
    Act Density 0.017%

    No Known Activations