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

    Neuronpedia

    INDEX
    Explanations

    SDK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Μέ
    -0.07
     therm
    -0.07
     WN
    -0.07
    wor
    -0.07
     trif
    -0.07
     wr
    -0.06
     Wahl
    -0.06
    �
    -0.06
     geg
    -0.06
     fish
    -0.06
    POSITIVE LOGITS
     defaultCenter
    0.07
     صنعت
    0.07
     SDK
    0.07
     sdk
    0.07
     SDL
    0.07
    SK
    0.07
    ック
    0.06
     GDK
    0.06
    dk
    0.06
    _xx
    0.06
    Act Density 0.003%

    No Known Activations