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

    Neuronpedia

    INDEX
    Explanations

    list continuation/ending

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    """,
    0.65
    "，
    0.63
     وي
    0.62
    ",$
    0.61
    》，
    0.61
    ហើយ
    0.61
    ”，
    0.60
    」，
    0.59
    மானது
    0.59
    தால்
    0.58
    POSITIVE LOGITS
     etc
    2.47
     등
    2.19
     등을
    2.17
     등이
    2.15
     등의
    2.12
    等
    2.07
    etc
    2.02
    などが
    2.00
    などを
    2.00
     आदि
    1.96
    Act Density 2.884%

    No Known Activations