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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忍
    -0.06
    geme
    -0.06
     professionalism
    -0.06
     cliffs
    -0.06
    BufferData
    -0.06
     Vk
    -0.06
    uvwxyz
    -0.06
     최신
    -0.06
    _TESTS
    -0.06
     prelim
    -0.06
    POSITIVE LOGITS
     louis
    0.07
    Double
    0.07
     Alexis
    0.06
     processing
    0.06
     duplex
    0.06
    Cookie
    0.06
     physically
    0.06
     Completion
    0.06
    öl
    0.06
     Figure
    0.06
    Act Density 0.000%

    No Known Activations