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

    Neuronpedia

    INDEX
    Explanations

    short term memory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     통한
    -0.09
    (Unity
    -0.08
    éticos
    -0.08
     провести
    -0.08
     ופ
    -0.08
     периода
    -0.08
    (Network
    -0.08
    “大
    -0.08
    (Camera
    -0.08
     Investors
    -0.08
    POSITIVE LOGITS
    sha
    0.08
     memory
    0.08
     transcript
    0.07
    /out
    0.07
     phenomenal
    0.07
    uss
    0.07
    DDR
    0.07
     SHA
    0.07
     memoria
    0.07
    Memory
    0.07
    Act Density 0.000%

    No Known Activations