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

    Neuronpedia

    INDEX
    Explanations

    initials and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ждение
    0.41
    abhuto
    0.40
    ⌵
    0.40
    <unused417>
    0.39
    ьера
    0.39
    ກັບ
    0.38
     embod
    0.38
     перио
    0.37
    আপনার
    0.37
    <=>
    0.37
    POSITIVE LOGITS
     J
    1.13
     M
    1.03
     R
    0.97
     C
    0.96
     H
    0.93
     A
    0.92
     G
    0.92
     S
    0.91
     L
    0.90
     B
    0.86
    Act Density 0.002%

    No Known Activations