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

    Neuronpedia

    INDEX
    Explanations

    common abbreviations and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     siglas
    0.46
    Enabled
    0.44
     acronym
    0.42
    enabled
    0.39
    -
    0.39
    GPU
    0.38
     står
    0.38
    yman
    0.37
    WORKS
    0.37
     терапии
    0.35
    POSITIVE LOGITS
    各种
    0.40
    cknowled
    0.39
    ค้า
    0.39
    ኼ
    0.38
    𒊑
    0.38
    naments
    0.38
    theit
    0.38
    बह
    0.37
    ઓને
    0.36
    म्मीद
    0.36
    Act Density 0.030%

    No Known Activations