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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idente
    0.37
    ('[
    0.36
     Junto
    0.35
    toFloat
    0.35
    onant
    0.35
     supl
    0.35
     cả
    0.34
     '{
    0.34
    दोनों
    0.34
     کنید
    0.34
    POSITIVE LOGITS
     Overseas
    0.37
     Abs
    0.36
    ostomy
    0.34
     Michael
    0.33
    ینی
    0.33
    дель
    0.32
     Respect
    0.32
    рі
    0.32
    food
    0.32
     School
    0.32
    Act Density 0.001%

    No Known Activations