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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.49
    IDE
    0.42
    MR
    0.42
    дук
    0.41
     kapas
    0.41
     Capacity
    0.41
    系統
    0.41
    ITER
    0.41
    PEL
    0.41
     Dysfunction
    0.40
    POSITIVE LOGITS
     пользова
    0.50
     eternal
    0.48
     renown
    0.45
    ंडन
    0.44
     brushes
    0.44
     exile
    0.43
     Ս
    0.43
    court
    0.43
     calligraphy
    0.43
     court
    0.42
    Act Density 0.003%

    No Known Activations