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

    Neuronpedia

    INDEX
    Explanations

    responds to questions and prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Defaults
    0.75
    强调
    0.73
    ไลน์
    0.70
     consideramos
    0.70
    色彩
    0.68
     justru
    0.68
    Responsible
    0.68
     عائد
    0.67
     enfat
    0.67
    acency
    0.67
    POSITIVE LOGITS
     questions
    1.80
     queries
    1.77
     requests
    1.61
     inquiries
    1.57
     Queries
    1.45
    questions
    1.44
     Questions
    1.42
     trivia
    1.40
     problems
    1.38
     query
    1.36
    Act Density 2.472%

    No Known Activations