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

    Neuronpedia

    INDEX
    Explanations

    continues or repeats for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ڕ
    0.42
     aikana
    0.42
     thé
    0.41
     doua
    0.40
     mű
    0.38
     două
    0.38
     én
    0.38
     приносит
    0.38
     awal
    0.38
     dva
    0.37
    POSITIVE LOGITS
     وهكذا
    0.99
     এভাবে
    0.77
     Similarly
    0.75
     similarly
    0.71
    等等
    0.71
     etc
    0.70
    Similarly
    0.70
    类似的
    0.69
     ইত্যাদি
    0.68
     seterusnya
    0.68
    Act Density 0.193%

    No Known Activations