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

    Neuronpedia

    INDEX
    Explanations

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Requirements
    0.20
     Similar
    0.20
     Analysis
    0.19
    此类
    0.19
     подоб
    0.19
     similaire
    0.18
     Try
    0.18
     ઓ
    0.18
     फीचर्स
    0.18
     Prior
    0.18
    POSITIVE LOGITS
    ንን
    0.23
     is
    0.22
    يا
    0.21
     mattina
    0.21
     entitles
    0.20
    యన
    0.20
     nedenle
    0.20
     was
    0.20
     morning
    0.19
    نګه
    0.19
    Act Density 0.054%

    No Known Activations