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

    Neuronpedia

    INDEX
    Explanations

    trading orders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نہيں
    0.60
     αν
    0.57
     sosten
    0.57
     زی
    0.57
     തവണ
    0.57
     ਨਹੀਂ
    0.56
     نہیں
    0.55
     હોય
    0.55
     iniziale
    0.55
     یا
    0.53
    POSITIVE LOGITS
    ناء
    0.50
    mensagem
    0.48
     Hastings
    0.46
    amas
    0.45
    чное
    0.45
    Компания
    0.45
     Бүген
    0.44
    مة
    0.44
     Большая
    0.43
    agens
    0.43
    Act Density 0.000%

    No Known Activations