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

    Neuronpedia

    INDEX
    Explanations

    rooms with bathrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     も
    0.85
    ﺍ
    0.85
    ﻑ
    0.85
     relacion
    0.81
    0.80
    ników
    0.76
    Κα
    0.76
    Чер
    0.76
    Ком
    0.75
     تلیفون
    0.75
    POSITIVE LOGITS
    ط
    1.12
    ס
    1.09
    ص
    1.03
    ت
    1.01
    m
    0.92
    ج
    0.90
    oo
    0.88
    ↵
    0.88
    n
    0.88
    ir
    0.85
    Act Density 0.002%

    No Known Activations