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

    Neuronpedia

    INDEX
    Explanations

    one at a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     próprio
    0.69
    jogador
    0.55
     otra
    0.55
    otum
    0.53
    мени
    0.53
     redondo
    0.52
     confid
    0.52
     adjacent
    0.52
     ٹھ
    0.52
    енты
    0.51
    POSITIVE LOGITS
    '.$
    0.85
    𝑖
    0.80
    𝑙
    0.74
    ḍ
    0.70
    𝑧
    0.68
    𝑒
    0.68
    𝑜
    0.64
     furlough
    0.64
    𝑐
    0.64
    ट
    0.63
    Act Density 0.027%

    No Known Activations