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

    Neuronpedia

    INDEX
    Explanations

    names and specific entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ने
    0.76
    គឺជា
    0.72
    лен
    0.70
     نے
    0.69
     нами
    0.69
     તરીકે
    0.68
     بوده
    0.68
     Cnemidophorus
    0.66
    glichkeiten
    0.66
     родился
    0.66
    POSITIVE LOGITS
    M
    0.90
     M
    0.89
    e
    0.78
    T
    0.75
    K
    0.74
    l
    0.73
    P
    0.73
     J
    0.72
     L
    0.72
    d
    0.70
    Act Density 0.069%

    No Known Activations