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

    Neuronpedia

    INDEX
    Explanations

    numbers and Chinese characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اکہ
    0.51
    pickMenu
    0.51
     vết
    0.50
     preponder
    0.50
     predom
    0.49
     balconies
    0.49
    連續
    0.49
    蠍
    0.48
    неоп
    0.48
     adoles
    0.47
    POSITIVE LOGITS
    2
    0.57
    3
    0.54
    k
    0.51
    5
    0.50
    4
    0.49
     P
    0.49
     water
    0.47
     /
    0.46
    之前
    0.45
    其
    0.45
    Act Density 0.015%

    No Known Activations