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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avacanam
    0.55
     Franti
    0.55
    gramModel
    0.54
    躹
    0.54
    ⴼ
    0.53
    ᕝ
    0.53
    Ƒ
    0.52
    赭
    0.52
    RELATIVA
    0.52
    試料
    0.52
    POSITIVE LOGITS
     dfs
    0.68
     DFS
    0.64
     nums
    0.63
    nums
    0.61
    dfs
    0.61
    leetcode
    0.60
    0.59
    DFS
    0.55
     helped
    0.52
     ev
    0.51
    Act Density 0.015%

    No Known Activations