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

    Neuronpedia

    INDEX
    Explanations

    24/7 or seamless access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ر
    0.24
     inmates
    0.23
    至於
    0.23
     axons
    0.23
     пита
    0.22
     SmackDown
    0.22
    bump
    0.22
     способности
    0.22
    которы
    0.22
     narciss
    0.22
    POSITIVE LOGITS
    šnj
    0.22
     wesentlich
    0.20
    त्ति
    0.20
    imensional
    0.20
    那就是
    0.20
     Anzeigen
    0.20
    場合には
    0.20
    .
    0.19
    edu
    0.19
    load
    0.19
    Act Density 0.428%

    No Known Activations