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

    Neuronpedia

    INDEX
    Explanations

    equations with x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ларды
    0.21
     ઘણા
    0.20
    🥸
    0.20
     purview
    0.20
    १८४
    0.20
    imately
    0.20
    Lycodon
    0.20
    plaza
    0.19
    łych
    0.19
    owanych
    0.19
    POSITIVE LOGITS
    x
    0.21
    u
    0.20
     किस
    0.19
    v
    0.19
     Cup
    0.18
    0
    0.18
     न
    0.18
    6
    0.18
    q
    0.17
    ymin
    0.17
    Act Density 0.152%

    No Known Activations