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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mockito
    -0.07
     جا
    -0.07
    _nc
    -0.07
    JA
    -0.06
    raně
    -0.06
    controllers
    -0.06
     dolar
    -0.06
    /auth
    -0.06
    /parser
    -0.06
    Pets
    -0.06
    POSITIVE LOGITS
     مستق
    0.07
     product
    0.07
     Constructor
    0.07
     competitor
    0.07
    _twitter
    0.07
    �
    0.07
     introduced
    0.07
     researcher
    0.06
     MARK
    0.06
    }}↵
    0.06
    Act Density 0.088%

    No Known Activations