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

    Neuronpedia

    INDEX
    Explanations

    new policy, pull request, hourly rate, Product Feedback, This song

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nomads
    0.56
     escrow
    0.47
     wrapped
    0.46
     trouvent
    0.45
     tulee
    0.45
     fleeing
    0.45
     populate
    0.44
     croire
    0.44
     evaporate
    0.44
     ベージュ
    0.43
    POSITIVE LOGITS
    આ
    0.47
    Excellent
    0.47
    ที่ดี
    0.45
    tos
    0.43
    Sach
    0.43
    As
    0.43
    Here
    0.43
    excellent
    0.42
    Taken
    0.42
     высокого
    0.42
    Act Density 0.021%

    No Known Activations