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

    Neuronpedia

    INDEX
    Explanations

    all else being equal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pit
    -0.07
    电压
    -0.07
    民主
    -0.07
     Election
    -0.07
    董事
    -0.07
     mine
    -0.06
    秘
    -0.06
    监狱
    -0.06
     gall
    -0.06
    興趣
    -0.06
    POSITIVE LOGITS
    大批
    0.09
     './
    0.07
     servi
    0.07
     Raised
    0.07
    .mod
    0.07
     значительно
    0.07
     CG
    0.07
    (rt
    0.07
     messageType
    0.07
    //--------------------------------
    0.07
    Act Density 0.009%

    No Known Activations