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

    Neuronpedia

    INDEX
    Explanations

    in this case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     начали
    0.40
     myself
    0.38
     amid
    0.38
    ៉
    0.36
     amidst
    0.36
     serotonin
    0.36
     Kishore
    0.36
     ole
    0.35
    罂
    0.35
     //-
    0.35
    POSITIVE LOGITS
     Pentru
    0.43
     کړ
    0.43
    解
    0.43
     केवल
    0.42
     uguale
    0.42
    खों
    0.42
    場合
    0.41
    해
    0.41
    วจ
    0.41
     फक्त
    0.39
    Act Density 0.050%

    No Known Activations