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

    Neuronpedia

    INDEX
    Explanations

    few followed by units of time or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BES
    0.49
     BS
    0.48
     and
    0.45
     noin
    0.42
     I
    0.42
     annat
    0.42
     one
    0.41
    akter
    0.41
     SVP
    0.41
     another
    0.41
    POSITIVE LOGITS
    몇
    1.23
    幾個
    1.05
    几
    1.04
    几个
    0.94
     wenige
    0.91
    幾
    0.90
     birkaç
    0.88
     wenigen
    0.87
     нескольких
    0.87
     dozen
    0.86
    Act Density 0.013%

    No Known Activations