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

    Neuronpedia

    INDEX
    Explanations

    words starting with Can or Kan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kunna
    1.20
    ang
    1.06
    क
    0.99
     poter
    0.96
     вот
    0.94
     знаком
    0.93
    i
    0.90
    𝗆
    0.90
     वस
    0.89
    ๊ก
    0.87
    POSITIVE LOGITS
    istered
    1.42
     artériel
    1.24
    berra
    1.24
    terbury
    1.22
    ADIAN
    1.21
     lakh
    1.15
    opies
    1.13
    vasser
    1.09
     ∣
    1.08
     hende
    1.08
    Act Density 0.125%

    No Known Activations