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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    整
    -0.07
     james
    -0.07
    easy
    -0.07
    oa
    -0.07
     f
    -0.07
    _<?
    -0.07
    𝑗
    -0.07
    gabe
    -0.07
     unchanged
    -0.06
    眼前
    -0.06
    POSITIVE LOGITS
     Collabor
    0.06
    BackgroundColor
    0.06
    ’all
    0.06
    {}↵↵
    0.06
    公开发
    0.06
    뿜
    0.06
     الأخ
    0.06
     THEM
    0.06
    懋
    0.06
    ਬ
    0.06
    Act Density 0.017%

    No Known Activations