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

    Neuronpedia

    INDEX
    Explanations

    Addresses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    изации
    -0.08
     MPU
    -0.08
    地面
    -0.07
     Persona
    -0.07
    מתר
    -0.07
    킨
    -0.07
    Used
    -0.07
    _BOTH
    -0.07
     Vĩnh
    -0.06
     servic
    -0.06
    POSITIVE LOGITS
    Курс
    0.07
    [date
    0.07
    排名
    0.07
    Negative
    0.07
     MILL
    0.06
     BRE
    0.06
     autos
    0.06
     bedroom
    0.06
    -table
    0.06
    (arc
    0.06
    Act Density 0.030%

    No Known Activations