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

    Neuronpedia

    INDEX
    Explanations

    provide me with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     мне
    0.50
     нам
    0.45
     हमें
    0.45
     आपल्याला
    0.44
     ہمیں
    0.42
     우리는
    0.39
     हमे
    0.39
     ನನಗೆ
    0.38
     nobis
    0.38
    ersi
    0.37
    POSITIVE LOGITS
    នូវ
    0.70
     some
    0.64
     plenty
    0.57
     a
    0.56
     lots
    0.54
    一些
    0.54
     everything
    0.52
     glimpses
    0.51
     something
    0.51
     einige
    0.50
    Act Density 0.053%

    No Known Activations