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

    Neuronpedia

    INDEX
    Explanations

    Site

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \Factories
    -0.08
    ńst
    -0.08
    PIO
    -0.07
    う
    -0.07
    izzes
    -0.07
    CHED
    -0.07
    WARD
    -0.07
     teste
    -0.07
     느
    -0.07
    ス
    -0.07
    POSITIVE LOGITS
    阿根廷
    0.08
     dominant
    0.07
    )</
    0.07
     Pant
    0.07
     ---↵
    0.07
     />↵
    0.07
    ]))↵
    0.07
    ,%
    0.07
    ��
    0.07
    )&
    0.07
    Act Density 0.020%

    No Known Activations