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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Đường
    -0.07
     HI
    -0.06
    rac
    -0.06
    े�
    -0.06
     Watkins
    -0.06
     favoured
    -0.06
     WhatsApp
    -0.06
     đồng
    -0.06
    datatype
    -0.06
    887
    -0.06
    POSITIVE LOGITS
    Creation
    0.07
    };↵↵↵↵
    0.07
     يج
    0.06
    _SCR
    0.06
     میک
    0.06
     disagreement
    0.06
     Vie
    0.06
     AJAX
    0.06
     شبکه
    0.06
     NONINFRINGEMENT
    0.06
    Act Density 0.256%

    No Known Activations