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

    Neuronpedia

    INDEX
    Explanations

    network relationships and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secretos
    0.42
     côte
    0.41
     Hé
    0.40
     ن
    0.40
     akt
    0.40
     mü
    0.40
     prend
    0.39
     متر
    0.39
     bureaucrats
    0.39
     Léon
    0.39
    POSITIVE LOGITS
    ти
    0.51
    Structure
    0.48
    TING
    0.48
    า
    0.48
    ALL
    0.47
    ANT
    0.47
    tions
    0.47
    ol
    0.47
    tion
    0.46
    某些
    0.46
    Act Density 0.119%

    No Known Activations