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

    Neuronpedia

    INDEX
    Explanations

    data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Often
    -0.10
    You've
    -0.10
     wonderfully
    -0.09
    ですよ
    -0.09
    Usually
    -0.09
     nicer
    -0.08
     oneself
    -0.08
    漂亮
    -0.08
    Brien
    -0.08
    疗
    -0.08
    POSITIVE LOGITS
     করেছি
    0.10
     gồm
    0.09
     ได้แก่
    0.08
     comprising
    0.08
     unprecedented
    0.08
     consisted
    0.08
     bomo
    0.08
    以下简称
    0.08
     consisting
    0.08
     ensured
    0.08
    Act Density 0.050%

    No Known Activations