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

    Neuronpedia

    INDEX
    Explanations

    Scale and magnification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Annotations
    -0.07
    Roy
    -0.07
    woke
    -0.07
     adorned
    -0.07
     Noise
    -0.07
     Dayton
    -0.07
    adioButton
    -0.06
    ovsky
    -0.06
    neapolis
    -0.06
    邹
    -0.06
    POSITIVE LOGITS
    住在
    0.07
     ```↵
    0.07
    _NET
    0.06
     пят
    0.06
     retir
    0.06
    并在
    0.06
    水质
    0.06
    เสมอ
    0.06
    _HARD
    0.06
    质量
    0.06
    Act Density 0.011%

    No Known Activations