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

    Neuronpedia

    INDEX
    Explanations

    code snippets with attribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     songwriter
    -0.07
     uninsured
    -0.07
     soluble
    -0.07
    pared
    -0.07
    出租
    -0.07
    .encode
    -0.07
     sovereign
    -0.07
     almond
    -0.07
    <decimal
    -0.07
    耶稣
    -0.07
    POSITIVE LOGITS
    שחר
    0.07
     замеча
    0.07
    棋牌游戏
    0.07
    🎋
    0.06
     đầy
    0.06
    Tri
    0.06
    家都知道
    0.06
    مديرية
    0.06
    .my
    0.06
    Stra
    0.06
    Act Density 0.001%

    No Known Activations