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

    Neuronpedia

    INDEX
    Explanations

    periods and commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rings
    0.58
    ring
    0.55
     ще
    0.54
    so
    0.52
     fists
    0.51
     rallying
    0.50
    spending
    0.50
    sorry
    0.50
    x
    0.49
    عاد
    0.48
    POSITIVE LOGITS
     podataka
    0.57
     سایټ
    0.54
    Ｐ
    0.52
     Uncomment
    0.51
     Import
    0.50
    Ｂ
    0.50
    出
    0.50
    评标
    0.49
     BLUENRG
    0.49
    ாராய
    0.48
    Act Density 0.000%

    No Known Activations