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

    Neuronpedia

    INDEX
    Explanations

    String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Panther
    -0.08
    transaction
    -0.07
    篆
    -0.07
     thuê
    -0.06
    -based
    -0.06
    _circle
    -0.06
    小狗
    -0.06
    _packages
    -0.06
    ﮃ
    -0.06
    	std
    -0.06
    POSITIVE LOGITS
     danych
    0.08
     délai
    0.07
    次の
    0.07
         ↵↵
    0.07
     giỏi
    0.07
     stagn
    0.07
     examinations
    0.07
     próxima
    0.07
    姻
    0.07
     dazz
    0.07
    Act Density 0.004%

    No Known Activations