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

    Neuronpedia

    INDEX
    Explanations

    integer operations, list sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    starcore
    0.52
    𒈬
    0.50
     mérid
    0.49
    𒊩
    0.49
     النسبيه
    0.47
    ImageAsset
    0.46
    テンツ
    0.45
    UserNotification
    0.45
    묽
    0.44
    沌
    0.43
    POSITIVE LOGITS
     nums
    0.95
     ans
    0.92
    nums
    0.91
    ans
    0.88
     dp
    0.78
    dp
    0.77
     dfs
    0.77
     DFS
    0.70
    Nums
    0.69
    Ans
    0.67
    Act Density 0.093%

    No Known Activations