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

    Neuronpedia

    INDEX
    Explanations

    how are you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eyelashes
    0.34
     координатами
    0.33
    asionally
    0.33
     ;\
    0.33
     tarses
    0.32
     newsc
    0.32
    鹑
    0.32
    -_-
    0.32
    aloko
    0.31
    젼
    0.31
    POSITIVE LOGITS
    que
    0.35
    ?!
    0.34
    Architect
    0.31
     sunt
    0.31
     re
    0.29
     breve
    0.28
     autem
    0.28
    am
    0.28
    ice
    0.28
    rem
    0.28
    Act Density 0.001%

    No Known Activations