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

    Neuronpedia

    INDEX
    Explanations

    abstract Chinese characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outros
    1.01
     vamos
    0.85
     jangan
    0.85
     mínimo
    0.84
     outro
    0.83
     when
    0.82
     cinco
    0.82
     quando
    0.81
     longa
    0.79
     🌱
    0.79
    POSITIVE LOGITS
    化
    0.79
    率
    0.77
    格
    0.74
    地
    0.73
    式
    0.73
    度
    0.72
    值
    0.71
    符
    0.71
    法
    0.69
    得
    0.69
    Act Density 0.031%

    No Known Activations