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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Somehow
    -0.07
     peacefully
    -0.07
    在玩家中
    -0.07
    屏幕上
    -0.07
     passports
    -0.07
     Tổ
    -0.07
     gerçekten
    -0.07
    埵
    -0.07
    学霸
    -0.06
    堤
    -0.06
    POSITIVE LOGITS
     menc
    0.08
     ما
    0.07
     عند
    0.07
     عمر
    0.07
    _at
    0.07
     życia
    0.07
    _behavior
    0.07
    .mark
    0.07
     MVC
    0.07
     мяс
    0.07
    Act Density 0.028%

    No Known Activations