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

    Neuronpedia

    INDEX
    Explanations

    give

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ساخت
    -0.07
    _RETURN
    -0.07
    畫
    -0.07
     Remove
    -0.07
     له
    -0.07
    教育
    -0.07
     werk
    -0.06
    cleanup
    -0.06
     Objective
    -0.06
     packaging
    -0.06
    POSITIVE LOGITS
    。「
    0.07
    だけど
    0.06
    _opt
    0.06
     Dire
    0.06
     Credentials
    0.06
     creo
    0.06
    .\"
    0.06
    .cum
    0.06
     Kul
    0.06
    .Xr
    0.06
    Act Density 0.018%

    No Known Activations