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

    Neuronpedia

    INDEX
    Explanations

    against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Transactional
    0.34
    ทำการ
    0.34
     அறு
    0.34
     বৃত্তি
    0.34
     Developing
    0.33
    etchup
    0.33
    estructive
    0.32
    Ɖ
    0.32
     travel
    0.32
     Travel
    0.32
    POSITIVE LOGITS
     against
    2.27
    against
    2.11
     против
    2.05
     Against
    2.03
    Against
    2.02
     gegen
    1.90
     melawan
    1.87
     AGAINST
    1.87
     ضد
    1.83
     tegen
    1.73
    Act Density 0.027%

    No Known Activations