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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Z
    -0.08
     applauded
    -0.07
    无
    -0.07
     yyn
    -0.07
     Pawn
    -0.06
     잘
    -0.06
     Actress
    -0.06
    巧克
    -0.06
     hostel
    -0.06
    -ms
    -0.06
    POSITIVE LOGITS
    BarItem
    0.07
    רי
    0.07
    -mount
    0.07
    ReturnValue
    0.07
    setEnabled
    0.07
    🖥
    0.07
    坊
    0.07
    ContentType
    0.07
    /live
    0.07
    𝐯
    0.07
    Act Density 0.148%

    No Known Activations