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

    Neuronpedia

    INDEX
    Explanations

    based on / relies on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    あなたが
    0.45
    )+'
    0.41
    ridges
    0.41
     joten
    0.41
    ចេ
    0.40
     फॉर
    0.39
     meanings
    0.39
    inander
    0.39
    で
    0.39
    แปล
    0.38
    POSITIVE LOGITS
     relies
    0.77
     dựa
    0.76
     rely
    0.74
     relying
    0.70
    依靠
    0.68
     basing
    0.64
     relied
    0.63
     Rely
    0.62
     basé
    0.61
     owes
    0.61
    Act Density 0.108%

    No Known Activations