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

    Neuronpedia

    INDEX
    Explanations

    availability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᠯ
    -0.09
    ISP
    -0.07
    蜞
    -0.07
    $email
    -0.07
    Ｘ
    -0.07
    贫血
    -0.07
     PdfP
    -0.07
     السلطات
    -0.07
    'We
    -0.07
     Colonel
    -0.07
    POSITIVE LOGITS
     milling
    0.07
    clipboard
    0.07
    Controllers
    0.07
    ";↵
    0.07
    attro
    0.07
    _transaksi
    0.06
     rav
    0.06
     Preferred
    0.06
    stricted
    0.06
    悲
    0.06
    Act Density 0.015%

    No Known Activations