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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    交
    0.66
     cubic
    0.64
     Manila
    0.64
     giao
    0.61
     আর্ক
    0.61
     क्यू
    0.60
    arct
    0.60
     Brunei
    0.59
     교
    0.58
     beech
    0.58
    POSITIVE LOGITS
     hail
    0.61
    SearchParams
    0.58
     Referral
    0.57
     overcome
    0.54
     kampany
    0.54
    Suzanne
    0.53
     campaign
    0.52
    Chain
    0.52
    Selectors
    0.52
     кампа
    0.52
    Act Density 0.000%

    No Known Activations