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

    Neuronpedia

    INDEX
    Explanations

    n <= 1 condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﮢ
    0.40
    廛
    0.40
     verkaufen
    0.39
    Melitaea
    0.39
    穰
    0.38
    醐
    0.38
    颢
    0.38
     людей
    0.37
    ფორმა
    0.37
     newApproved
    0.37
    POSITIVE LOGITS
    3
    0.46
    1
    0.41
    三个
    0.36
    ame
    0.35
    arti
    0.33
    zing
    0.33
    js
    0.33
    xor
    0.33
    go
    0.32
     inc
    0.32
    Act Density 0.006%

    No Known Activations