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

    Neuronpedia

    INDEX
    Explanations

    lists and combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espl
    1.33
    Tort
    1.32
     നിൽ
    1.28
     bu
    1.26
    ched
    1.23
    ানো
    1.22
    Referee
    1.21
    ʼn
    1.19
     ഏറ്റവും
    1.18
     decir
    1.16
    POSITIVE LOGITS
    م
    1.32
    ্র
    1.32
    ён
    1.14
    если
    1.14
     решать
    1.14
    ت
    1.12
    hardware
    1.09
    項目
    1.08
     предпринима
    1.06
    ાર
    1.05
    Act Density 0.000%

    No Known Activations