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

    Neuronpedia

    INDEX
    Explanations

    numbers and multiplicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     각종
    0.39
     snart
    0.36
     ン
    0.35
    衔
    0.35
    鹃
    0.35
     عن
    0.34
     我的
    0.34
     ไ
    0.33
     اخ
    0.33
     ఇతర
    0.33
    POSITIVE LOGITS
     simultaneous
    0.75
     multiple
    0.62
     simultaneously
    0.61
    複数
    0.59
    複数の
    0.58
    同时
    0.57
    同時に
    0.57
    Multiple
    0.56
     simult
    0.55
     Simultaneous
    0.55
    Act Density 0.359%

    No Known Activations