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

    Neuronpedia

    INDEX
    Explanations

    who wrote / released

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅದು
    0.46
     അത്
    0.38
     addition
    0.38
     ինչ
    0.37
     అది
    0.37
     прямо
    0.36
     ნახ
    0.36
     उमेदवार
    0.36
    endium
    0.35
    ুগত্য
    0.35
    POSITIVE LOGITS
    ৳
    0.42
     sle
    0.36
    트
    0.36
    哫
    0.35
    -'
    0.35
     যশোর
    0.35
     linestyle
    0.35
     svůj
    0.35
    פ
    0.34
     मान
    0.34
    Act Density 0.001%

    No Known Activations