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

    Neuronpedia

    INDEX
    Explanations

    set to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⊟
    0.42
    amet
    0.41
    䇝
    0.40
    াভাবিক
    0.38
     चलन
    0.38
    SKA
    0.38
    พร้อม
    0.37
    褛
    0.37
    archiw
    0.36
    rowset
    0.36
    POSITIVE LOGITS
     ComVisible
    0.49
     up
    0.40
     giá
    0.40
     DSS
    0.39
     Blast
    0.38
    ssc
    0.37
     Up
    0.37
     Tz
    0.37
    פור
    0.36
     ob
    0.35
    Act Density 0.001%

    No Known Activations