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

    Neuronpedia

    INDEX
    Explanations

    legal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rent
    -0.07
     AuthenticationService
    -0.07
    حي
    -0.06
     部
    -0.06
    _params
    -0.06
    background
    -0.06
     tow
    -0.06
    ™
    -0.06
    aly
    -0.06
    respond
    -0.06
    POSITIVE LOGITS
     timezone
    0.06
     stre
    0.06
    мін
    0.06
     досить
    0.06
     Lebanese
    0.06
    _CLICKED
    0.06
    Ｋ
    0.06
     occupies
    0.06
     Tencent
    0.06
     Tibet
    0.05
    Act Density 0.016%

    No Known Activations