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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ์อ
    -0.07
    实际
    -0.06
    DOC
    -0.06
    antd
    -0.06
    díl
    -0.06
    xea
    -0.06
     Да
    -0.06
     NSMutableArray
    -0.06
    olta
    -0.06
     dancing
    -0.05
    POSITIVE LOGITS
     })↵↵
    0.07
     excluded
    0.07
    ')));↵↵
    0.07
    εύ
    0.07
    ;',↵
    0.07
     KERNEL
    0.07
     кг
    0.07
    ]},
    0.07
    --------↵↵
    0.07
    "),↵↵
    0.07
    Act Density 0.005%

    No Known Activations