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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personaggi
    0.81
     personaje
    0.76
     adhik
    0.76
    ໝ
    0.73
    <unused84>
    0.72
     utilisateur
    0.71
    kiej
    0.70
     separ
    0.70
     diberikan
    0.70
    人物
    0.69
    POSITIVE LOGITS
    рін
    0.64
    ಗ್ರ
    0.63
     painfully
    0.63
     सोचा
    0.61
     करती
    0.60
     આગળ
    0.59
     интере
    0.58
    cores
    0.58
     تكلم
    0.57
    мпания
    0.57
    Act Density 0.003%

    No Known Activations