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

    Neuronpedia

    INDEX
    Explanations

    common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASCADE
    -0.06
    atten
    -0.06
    乗
    -0.06
    issan
    -0.06
    -flow
    -0.06
    рії
    -0.06
    џџџџџџџџ
    -0.06
    еп
    -0.06
    flate
    -0.06
     narrator
    -0.05
    POSITIVE LOGITS
     Zh
    0.07
     Seriously
    0.07
    语
    0.07
    الث
    0.07
    .percent
    0.07
     configFile
    0.07
    Seriously
    0.07
     connecting
    0.06
     sho
    0.06
     External
    0.06
    Act Density 0.160%

    No Known Activations