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

    Neuronpedia

    INDEX
    Explanations

    time, start, or detection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manson
    -0.07
     plainly
    -0.07
    תיב
    -0.07
    textarea
    -0.07
    ấp
    -0.07
     thần
    -0.07
    慨
    -0.07
    ì
    -0.07
     па
    -0.07
    __↵
    -0.07
    POSITIVE LOGITS
    点亮
    0.08
    羽毛
    0.07
    ཏ
    0.07
     rebuild
    0.07
    中国制造
    0.07
    ✨
    0.07
    走路
    0.06
    ITS
    0.06
    棱
    0.06
    一件事情
    0.06
    Act Density 0.044%

    No Known Activations