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

    Neuronpedia

    INDEX
    Explanations

    code snippets and function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.91
     -
    0.82
      
    0.79
    .
    0.77
     –
    0.76
     or
    0.70
     (
    0.69
    ↵↵
    0.67
     particularly
    0.65
    -
    0.65
    POSITIVE LOGITS
     함수
    1.11
    字符串
    1.08
    TreeNode
    1.06
    数组
    1.04
    polynomial
    1.03
     букмекерлер
    1.03
    函数
    1.00
    inputFile
    0.99
    ListNode
    0.98
    𒌦
    0.97
    Act Density 0.188%

    No Known Activations