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

    Neuronpedia

    INDEX
    Explanations

    explanations of why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     জল
    0.47
     gallon
    0.46
     chol
    0.46
     cah
    0.46
     nguồn
    0.46
     lon
    0.44
     lá
    0.43
     marrow
    0.43
     water
    0.43
     rainforest
    0.43
    POSITIVE LOGITS
    Before
    0.48
    Revised
    0.47
    revise
    0.47
    analisi
    0.46
    靥
    0.43
    Editing
    0.42
    Sebelum
    0.41
    ตัดสิน
    0.41
     предвари
    0.41
    മൂ
    0.40
    Act Density 0.168%

    No Known Activations