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

    Neuronpedia

    INDEX
    Explanations

    School grades

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forests
    -0.07
     nieu
    -0.06
    also
    -0.06
    *M
    -0.06
    ramid
    -0.06
     ánh
    -0.06
    -url
    -0.06
     зас
    -0.06
    FileInfo
    -0.06
     العديد
    -0.06
    POSITIVE LOGITS
    如果
    0.08
     :/:
    0.07
    (DWORD
    0.07
    (nil
    0.07
     NotImplemented
    0.07
     narcotics
    0.07
    場合
    0.06
    WASHINGTON
    0.06
    #+
    0.06
    шин
    0.06
    Act Density 0.009%

    No Known Activations