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

    Neuronpedia

    INDEX
    Explanations

    say “like”

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ՛
    -0.10
     àti
    -0.09
    ૦
    -0.09
    ურთ
    -0.08
    Չ
    -0.08
    એક
    -0.08
     จุด
    -0.08
     oversees
    -0.08
     ўдз
    -0.08
     მონაწილ
    -0.08
    POSITIVE LOGITS
    比如
    0.10
     כגון
    0.09
    ，例如
    0.09
     כמו
    0.09
     like
    0.09
    ，比如
    0.08
     যেমন
    0.08
    例如
    0.08
     regarding
    0.08
    :↵↵
    0.08
    Act Density 0.011%

    No Known Activations