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

    Neuronpedia

    INDEX
    Explanations

    symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compressed
    -0.07
     aisle
    -0.07
     besonders
    -0.07
     axis
    -0.07
    (database
    -0.07
     제공
    -0.07
    ющей
    -0.06
     paris
    -0.06
     seq
    -0.06
    Directories
    -0.06
    POSITIVE LOGITS
    ])↵
    0.06
     aylık
    0.06
    ])),↵
    0.06
     행동
    0.06
     IOCTL
    0.06
    \Message
    0.06
    。↵
    0.06
     bez
    0.06
    <AM
    0.06
    ）↵↵
    0.06
    Act Density 0.041%

    No Known Activations