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

    Neuronpedia

    INDEX
    Explanations

    numbers after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hiqdev
    0.70
    ൨
    0.70
    ្សា
    0.68
     பிரசா
    0.67
    رب
    0.67
    𝐳
    0.66
    ಾನೂ
    0.66
    ൪
    0.66
    பிலோ
    0.64
    agena
    0.64
    POSITIVE LOGITS
      
    0.81
     (
    0.80
     {
    0.75
     $
    0.74
    .
    0.73
    ↵
    0.71
     "
    0.71
     '
    0.71
    K
    0.70
    ↵↵
    0.70
    Act Density 0.653%

    No Known Activations