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
     Juan
    -0.07
     множе
    -0.07
    628
    -0.07
     programmers
    -0.06
    める
    -0.06
    Juan
    -0.06
     côt
    -0.06
    <Expression
    -0.06
    @implementation
    -0.06
    260
    -0.06
    POSITIVE LOGITS
    ㅋㅋㅋㅋ
    0.07
     jasmine
    0.06
     -------
    0.06
     Agreement
    0.06
    _NT
    0.06
     внимание
    0.06
    BufferSize
    0.06
    ╗
    0.06
    _so
    0.06
     Waste
    0.06
    Act Density 0.080%

    No Known Activations