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

    Neuronpedia

    INDEX
    Explanations

    mechanics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mong
    -0.07
    (flags
    -0.07
     colabor
    -0.06
    γχ
    -0.06
     misunderstanding
    -0.06
    дж
    -0.06
     glBegin
    -0.06
    kee
    -0.06
     sagen
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     millennials
    0.08
    システム
    0.07
    -quote
    0.07
     "//
    0.07
    .driver
    0.07
     corporations
    0.07
     systems
    0.07
     phenomenal
    0.06
    '</
    0.06
     admins
    0.06
    Act Density 0.005%

    No Known Activations