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

    Neuronpedia

    INDEX
    Explanations

    lush

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     áreas
    -0.08
     мам
    -0.07
    _PHONE
    -0.07
    נתי
    -0.07
    利
    -0.07
    spoken
    -0.07
     spas
    -0.07
     распространен
    -0.07
    小白
    -0.07
    比较大
    -0.06
    POSITIVE LOGITS
    一心
    0.08
    坚实的
    0.07
    (uid
    0.07
    箖
    0.06
     destroying
    0.06
     interrupt
    0.06
    都被
    0.06
    Reader
    0.06
    AR
    0.06
    𫟼
    0.06
    Act Density 0.002%

    No Known Activations