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

    Neuronpedia

    INDEX
    Explanations

    specialized terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soul
    0.45
    du
    0.44
    son
    0.44
    K
    0.43
    نا
    0.41
    O
    0.41
     also
    0.41
    D
    0.41
    Home
    0.40
     également
    0.40
    POSITIVE LOGITS
    .}\
    0.52
     enfoque
    0.52
     experto
    0.50
     সিলে
    0.49
     competenze
    0.48
     фор
    0.48
     alguno
    0.48
     терми
    0.47
     herramientas
    0.47
     технологи
    0.47
    Act Density 0.013%

    No Known Activations