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

    Neuronpedia

    INDEX
    Explanations

    Gear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATRIX
    -0.07
    θρω
    -0.06
    تف
    -0.06
    _minus
    -0.06
     tul
    -0.06
     надо
    -0.06
    电话
    -0.06
     зрения
    -0.06
    아서
    -0.06
    ايت
    -0.06
    POSITIVE LOGITS
     scouting
    0.07
     Media
    0.07
     대한민국
    0.07
     karak
    0.07
    team
    0.06
    contra
    0.06
     holdings
    0.06
     CN
    0.06
    .InnerException
    0.06
     educate
    0.06
    Act Density 0.001%

    No Known Activations