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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त्
    0.39
    指導
    0.39
    DT
    0.38
    tx
    0.35
    CN
    0.35
    MA
    0.35
    Critical
    0.35
     lý
    0.34
     consolidated
    0.34
     tiểu
    0.34
    POSITIVE LOGITS
     Anbieter
    0.44
    bedaan
    0.43
     аксессу
    0.43
    拯
    0.42
     Telef
    0.42
    wärm
    0.41
     hitta
    0.41
     scathing
    0.41
    এছ
    0.40
     appalling
    0.40
    Act Density 0.000%

    No Known Activations