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

    Neuronpedia

    INDEX
    Explanations

    rates, experimental, prospective study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ির
    1.18
     apre
    1.15
    ственно
    1.14
    ло
    1.11
     सॉल्यू
    1.10
     выяс
    1.09
    чика
    1.09
    খা
    1.08
    emente
    1.08
     предпоч
    1.07
    POSITIVE LOGITS
    ges
    1.33
    $(".
    1.32
    k
    1.19
    as
    1.17
    চ্ছেদ
    1.16
     gelegt
    1.14
     vegetarians
    1.13
    đenja
    1.13
    関東
    1.11
     preceded
    1.10
    Act Density 0.000%

    No Known Activations