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

    Neuronpedia

    INDEX
    Explanations

    Two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     işlet
    -0.08
    allows
    -0.07
     zaten
    -0.07
    pak
    -0.07
     Competitive
    -0.07
     meisje
    -0.06
    ZD
    -0.06
     patiently
    -0.06
     admin
    -0.06
    Disallow
    -0.06
    POSITIVE LOGITS
    ToDate
    0.07
    했
    0.07
     Purdue
    0.06
     трет
    0.06
     потрап
    0.06
    Moment
    0.06
    Ông
    0.06
     recovered
    0.06
    otent
    0.06
    .QRect
    0.06
    Act Density 0.006%

    No Known Activations