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

    Neuronpedia

    INDEX
    Explanations

    path or name assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Allow
    1.09
    azol
    1.01
     jotka
    0.97
    etera
    0.88
     चोर
    0.87
    ការ
    0.87
    ornos
    0.86
     некоторы
    0.86
     hasilnya
    0.86
    achusetts
    0.86
    POSITIVE LOGITS
    ০১
    0.99
    Все
    0.93
    犟
    0.92
     paraphrase
    0.90
     aspirant
    0.87
    Ти
    0.86
    אָ
    0.86
     UserName
    0.86
    不明
    0.84
    UserName
    0.84
    Act Density 0.255%

    No Known Activations