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

    Neuronpedia

    INDEX
    Explanations

    explaining why something works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तस्वी
    0.53
     ParkingLot
    0.50
     taxa
    0.50
     tax
    0.49
     recipe
    0.48
     taxes
    0.48
     tagReport
    0.48
     econometric
    0.48
     ObjData
    0.46
     equipamento
    0.46
    POSITIVE LOGITS
    的地
    0.54
    ו
    0.52
    ösung
    0.49
    à
    0.48
    ò
    0.48
    或
    0.47
    łym
    0.46
    Free
    0.46
    ό
    0.46
     或
    0.46
    Act Density 0.002%

    No Known Activations