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

    Neuronpedia

    INDEX
    Explanations

    numerical conversions and estimations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ګه
    0.46
    swers
    0.45
    ूटूथ
    0.44
    ষ্কার
    0.44
    墂
    0.44
    䡒
    0.44
    欳
    0.43
    ktCap
    0.43
    міна
    0.43
    Pedido
    0.43
    POSITIVE LOGITS
     See
    0.55
    ↵
    0.52
     -
    0.50
     (
    0.49
     Learn
    0.49
     Reverse
    0.47
     Write
    0.46
     Convert
    0.46
     Correct
    0.45
    es
    0.44
    Act Density 0.002%

    No Known Activations