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

    Neuronpedia

    INDEX
    Explanations

    python code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     који
    0.48
     cómod
    0.48
     cómodo
    0.47
    rà
    0.43
     роско
    0.43
     cómoda
    0.42
    му
    0.41
    lake
    0.40
     سواء
    0.40
    رر
    0.39
    POSITIVE LOGITS
    getPage
    0.45
     aktivit
    0.43
     the
    0.42
    上午
    0.41
     representing
    0.40
    ั่วโมง
    0.40
    শিক্ষ
    0.39
    ۹
    0.39
     WORLD
    0.39
    Де
    0.39
    Act Density 0.000%

    No Known Activations