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

    Neuronpedia

    INDEX
    Explanations

    defining a location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strutture
    0.61
    0.58
    最小
    0.58
    ቑ
    0.58
    ئين
    0.57
    第一次
    0.56
    راهيم
    0.56
    ς
    0.56
    يمان
    0.55
    大
    0.55
    POSITIVE LOGITS
     Location
    0.98
     getLocation
    0.89
    is
    0.84
    location
    0.83
    ig
    0.81
    Location
    0.79
    า
    0.79
     by
    0.75
     Locations
    0.74
    amu
    0.73
    Act Density 0.028%

    No Known Activations