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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রোগীর
    0.44
    维修
    0.40
    েন্টের
    0.40
    服务的
    0.40
     چڑھ
    0.39
     रुग्
    0.39
    晔
    0.39
    褙
    0.38
    hôpital
    0.38
    ிறேன்
    0.38
    POSITIVE LOGITS
     iguais
    0.39
     iguales
    0.36
     identique
    0.36
     l
    0.35
    平安
    0.35
    сера
    0.35
     identiques
    0.34
     azon
    0.34
     youre
    0.34
    ᱢ
    0.34
    Act Density 0.002%

    No Known Activations