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

    Neuronpedia

    INDEX
    Explanations

    words followed by "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    柺
    0.61
     katika
    0.59
    超过
    0.59
     nella
    0.57
    muj
    0.57
    rubyg
    0.55
    ܤ
    0.55
    ớt
    0.54
    ApiResponse
    0.54
     উচ্চার
    0.53
    POSITIVE LOGITS
     In
    3.08
    In
    3.03
    IN
    2.95
     IN
    2.94
    イン
    2.71
     ইন
    2.38
    in
    2.27
     inn
    2.24
    ইন
    2.20
     इन
    2.17
    Act Density 0.701%

    No Known Activations