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

    Neuronpedia

    INDEX
    Explanations

    a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Objection
    0.60
     any
    0.58
    ).
    0.57
     atau
    0.57
     TextView
    0.57
     或者
    0.55
    ,
    0.55
     oppure
    0.54
     หรือ
    0.54
     someone
    0.54
    POSITIVE LOGITS
     ત્રણ
    0.65
    大規模
    0.57
    精心
    0.55
     नामक
    0.52
     tzv
    0.52
     अत्याधुनिक
    0.51
     혁
    0.51
     высоко
    0.50
    小型
    0.50
     آزمایش
    0.50
    Act Density 0.177%

    No Known Activations