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

    Neuronpedia

    INDEX
    Explanations

    recycling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ave
    -0.07
     Trees
    -0.07
     Sar
    -0.07
     ACS
    -0.07
    ्वव
    -0.07
    AVE
    -0.06
    Paren
    -0.06
     وف
    -0.06
    _LOW
    -0.06
    _callbacks
    -0.06
    POSITIVE LOGITS
     flashed
    0.06
    ﾆ
    0.06
     "~/
    0.06
    ／:
    0.06
     Additionally
    0.06
     gradually
    0.06
    -lived
    0.06
     generalized
    0.06
     dış
    0.05
    샵
    0.05
    Act Density 0.029%

    No Known Activations