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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     після
    -0.07
    took
    -0.07
     sur
    -0.07
    ُّ
    -0.07
    集团
    -0.07
    Mate
    -0.07
     tường
    -0.06
    ント
    -0.06
     dů
    -0.06
     Sür
    -0.06
    POSITIVE LOGITS
    _OCC
    0.07
    (sr
    0.06
     doGet
    0.06
     Safe
    0.06
    /py
    0.06
     Blogger
    0.06
    _ARM
    0.06
    .x
    0.06
     ↵↵
    0.06
     Ange
    0.06
    Act Density 0.000%

    No Known Activations