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

    Neuronpedia

    INDEX
    Explanations

    single quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вд
    -0.06
     involve
    -0.06
    ž
    -0.06
    =DB
    -0.06
    -led
    -0.06
     Land
    -0.06
     wounded
    -0.06
     dead
    -0.06
     Electron
    -0.06
     analytic
    -0.06
    POSITIVE LOGITS
    ＼＼
    0.08
    änder
    0.07
     vàng
    0.07
    .netflix
    0.07
     �
    0.07
     cherry
    0.06
    แท
    0.06
     stu
    0.06
    ransition
    0.06
    etcode
    0.06
    Act Density 0.014%

    No Known Activations