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

    Neuronpedia

    INDEX
    Explanations

    variety of topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    变异
    -0.08
     rouge
    -0.07
    _eta
    -0.07
    -0.07
    一族
    -0.07
    ᨩ
    -0.06
     compromised
    -0.06
    豆
    -0.06
    ﷽
    -0.06
     possibilità
    -0.06
    POSITIVE LOGITS
    끈
    0.08
    叹了
    0.08
    详细介绍
    0.07
     "'",
    0.07
    Labels
    0.07
    Α
    0.07
    ắc
    0.07
    声誉
    0.07
    -Length
    0.07
     />,
    0.07
    Act Density 0.363%

    No Known Activations