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

    Neuronpedia

    INDEX
    Explanations

    Spanish/Italian text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identify
    -0.07
     мона
    -0.06
     vlak
    -0.06
    одатель
    -0.06
     ghi
    -0.06
     bohat
    -0.06
     mẹ
    -0.06
    oğan
    -0.06
     hugs
    -0.06
     parental
    -0.06
    POSITIVE LOGITS
     sentido
    0.14
     Sinn
    0.08
    τα
    0.06
     teens
    0.06
    isObject
    0.06
     IconData
    0.06
    诉
    0.06
     Attendance
    0.06
    意义
    0.06
    ء
    0.06
    Act Density 0.007%

    No Known Activations