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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     програм
    -0.07
     romantic
    -0.06
     万
    -0.06
    (newUser
    -0.06
    tk
    -0.06
     sour
    -0.06
    -й
    -0.06
    ############################################################################
    -0.06
    Var
    -0.06
    .ListBox
    -0.06
    POSITIVE LOGITS
    unsqueeze
    0.06
    058
    0.06
     json
    0.06
     ''.
    0.06
    RES
    0.06
     тек
    0.06
    Coder
    0.06
     Sleeping
    0.06
     puedes
    0.06
     imperialism
    0.06
    Act Density 0.058%

    No Known Activations