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

    Neuronpedia

    INDEX
    Explanations

    Eu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _numero
    -0.07
    茂
    -0.07
    -license
    -0.07
    庞大
    -0.07
    展现
    -0.06
    gender
    -0.06
    颂
    -0.06
    暕
    -0.06
     throne
    -0.06
    mani
    -0.06
    POSITIVE LOGITS
     Eu
    0.08
    /output
    0.08
    ,{
    0.07
    ]],↵
    0.07
    {}↵
    0.07
    .pth
    0.07
     Lu
    0.07
    /';↵
    0.07
    ]]
↵
    0.07
    に向
    0.07
    Act Density 0.007%

    No Known Activations