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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     استر
    -0.07
    ніх
    -0.06
     брос
    -0.06
    ７
    -0.06
     ffm
    -0.06
    /post
    -0.06
    永久
    -0.06
    	cp
    -0.06
    uien
    -0.06
    しよう
    -0.06
    POSITIVE LOGITS
    .Tele
    0.07
     UT
    0.06
    Confirm
    0.06
     NT
    0.06
    _AS
    0.06
    ,S
    0.06
     bike
    0.06
     Gabriel
    0.06
    Dt
    0.06
     seat
    0.06
    Act Density 0.226%

    No Known Activations