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

    Neuronpedia

    INDEX
    Explanations

    email headers and origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     José
    0.44
     Jose
    0.41
     rời
    0.39
     runaway
    0.39
     departure
    0.38
     Albanese
    0.38
     دینی
    0.37
     अनु
    0.37
     Sod
    0.37
    departure
    0.37
    POSITIVE LOGITS
    Received
    0.50
     Received
    0.46
     Receipt
    0.46
    Origin
    0.45
    Receipt
    0.44
     Origin
    0.41
    Generating
    0.41
    Color
    0.40
     received
    0.40
     originated
    0.40
    Act Density 0.001%

    No Known Activations