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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لما
    0.63
    ГА
    0.62
     Plastic
    0.61
     выбира
    0.60
    Plastic
    0.59
     Ratt
    0.59
     Hobbs
    0.59
     каким
    0.59
     Daya
    0.59
     unbound
    0.59
    POSITIVE LOGITS
     consumidores
    0.58
     القناه
    0.58
     EVER
    0.57
    蔗
    0.55
     măsur
    0.54
    ্মদ
    0.53
    添加到
    0.52
    範
    0.52
    叅
    0.52
     mercado
    0.52
    Act Density 0.000%

    No Known Activations