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

    Neuronpedia

    INDEX
    Explanations

    descriptive phrases about attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тоже
    0.32
    एशन
    0.32
    Honestly
    0.32
    酺
    0.32
     разных
    0.31
     dólares
    0.31
     честь
    0.30
     Вообще
    0.30
     êtres
    0.30
    ඍ
    0.30
    POSITIVE LOGITS
     firstly
    0.45
     primarily
    0.43
     extracting
    0.40
     three
    0.39
     selecting
    0.39
     combining
    0.38
     designing
    0.38
     mainly
    0.37
     establishing
    0.37
     threefold
    0.37
    Act Density 0.041%

    No Known Activations