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

    Neuronpedia

    INDEX
    Explanations

    specific instance or part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ellations
    0.77
    пуляр
    0.67
    اعری
    0.66
     กี่
    0.65
    evsky
    0.65
     পুনরুদ্ধ
    0.65
     たり
    0.64
    ausible
    0.64
    වි
    0.64
    erci
    0.63
    POSITIVE LOGITS
     Option
    1.96
     Chapter
    1.86
     Section
    1.84
     Step
    1.77
     Episode
    1.73
     Module
    1.73
     Phase
    1.73
     Item
    1.72
     Stage
    1.69
     Version
    1.65
    Act Density 0.662%

    No Known Activations