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

    Neuronpedia

    INDEX
    Explanations

    Military and weapons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ************************************************
    -0.07
     fung
    -0.07
     gated
    -0.06
    圆满
    -0.06
     hver
    -0.06
    	So
    -0.06
    _rooms
    -0.06
     guten
    -0.06
    !!!!↵↵
    -0.06
    .hom
    -0.06
    POSITIVE LOGITS
    ȧ
    0.07
    用户名
    0.07
    Epoch
    0.07
    人たち
    0.07
    骼
    0.07
    塥
    0.07
    足以
    0.07
    �
    0.06
    تباع
    0.06
    馌
    0.06
    Act Density 0.025%

    No Known Activations