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

    Neuronpedia

    INDEX
    Explanations

    sup followed by common endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    気に
    0.41
    REZ
    0.41
    [
    0.40
    rène
    0.40
    ğun
    0.40
    risome
    0.39
    િયન
    0.38
    orant
    0.38
    ivalent
    0.37
     int
    0.37
    POSITIVE LOGITS
    Sup
    0.67
     Supers
    0.58
     Sup
    0.57
    supers
    0.56
     supers
    0.54
     supp
    0.50
     sup
    0.50
     suppl
    0.49
    sup
    0.49
     Supp
    0.46
    Act Density 0.001%

    No Known Activations