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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -tool
    -0.06
    बर
    -0.06
    nan
    -0.06
    セ
    -0.06
    _mi
    -0.06
     McKay
    -0.06
    aversal
    -0.06
    ei
    -0.06
     porn
    -0.05
     провед
    -0.05
    POSITIVE LOGITS
    歲
    0.08
     ####
    0.08
    融
    0.07
    urum
    0.06
    。而
    0.06
     "/",
    0.06
    (schema
    0.06
    (route
    0.06
    (prod
    0.06
     اقتص
    0.06
    Act Density 0.004%

    No Known Activations