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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DL
    -0.06
     sv
    -0.06
     cp
    -0.06
     superiority
    -0.06
     SEA
    -0.06
    Prim
    -0.06
     نش
    -0.06
     Reception
    -0.06
     oil
    -0.06
     сб
    -0.06
    POSITIVE LOGITS
    .JLabel
    0.07
    uslim
    0.07
    -desktop
    0.07
    neck
    0.07
    0.06
    هن
    0.06
    сом
    0.06
    ZA
    0.06
    .ByteString
    0.06
    .mvc
    0.06
    Act Density 0.002%

    No Known Activations