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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ريق
    -0.07
    ataires
    -0.07
    ㌘
    -0.07
    (newValue
    -0.07
    قر
    -0.07
     committed
    -0.06
    _image
    -0.06
    Ộ
    -0.06
    麑
    -0.06
    ประกาศ
    -0.06
    POSITIVE LOGITS
     blank
    0.10
    ENTION
    0.08
    芍
    0.07
    ]bool
    0.07
     ach
    0.07
     ≤
    0.07
    ="../../
    0.07
     typing
    0.07
     SPI
    0.06
    .tick
    0.06
    Act Density 0.024%

    No Known Activations