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

    Neuronpedia

    INDEX
    Explanations

    numeric values with decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    禳
    0.29
    OnFileChange
    0.29
    েন্ত্র
    0.28
    ों
    0.27
    nBitCount
    0.27
     கற்ற
    0.26
    BeforeText
    0.26
    BySize
    0.26
     UICtrl
    0.26
    sadquotes
    0.26
    POSITIVE LOGITS
     was
    0.36
    er
    0.35
    m
    0.33
    u
    0.33
    5
    0.32
    y
    0.31
    ↵
    0.31
    i
    0.31
     for
    0.31
     can
    0.30
    Act Density 0.147%

    No Known Activations