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

    Neuronpedia

    INDEX
    Explanations

    Job postings and employment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    of
    -0.07
    Creates
    -0.07
     averaged
    -0.06
    줫
    -0.06
    厚
    -0.06
    省级
    -0.06
    ❰
    -0.06
     初始化
    -0.06
    阐
    -0.06
    镊
    -0.06
    POSITIVE LOGITS
    _inline
    0.07
    잠
    0.07
     Patrol
    0.07
     Warcraft
    0.07
    新型
    0.07
    ды
    0.07
    One
    0.07
    _tab
    0.06
     ""
↵
    0.06
    Company
    0.06
    Act Density 0.032%

    No Known Activations