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

    Neuronpedia

    INDEX
    Explanations

    mathematical descriptions and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sponsoring
    0.49
     مشا
    0.47
    hamed
    0.45
     revamped
    0.45
     revamp
    0.44
     콘텐츠
    0.44
     sponsorships
    0.44
     concerts
    0.43
    高品質
    0.43
     multifunctional
    0.43
    POSITIVE LOGITS
     logarith
    0.66
     πίνακα
    0.64
     Tabelle
    0.62
     logarithm
    0.62
     angegeben
    0.61
     modulo
    0.57
     Aufgabe
    0.57
     polinom
    0.57
     Zahlen
    0.57
     liczb
    0.57
    Act Density 0.015%

    No Known Activations