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

    Neuronpedia

    INDEX
    Explanations

    elements within linked lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Needed
    0.58
    ก่อ
    0.58
    W
    0.55
    น่า
    0.53
    เคย
    0.51
     Dump
    0.51
     لتح
    0.51
     вот
    0.51
     우리는
    0.51
     μας
    0.51
    POSITIVE LOGITS
    整数
    1.01
     integers
    1.01
     integer
    0.98
     调用
    0.93
    文字列
    0.93
     salario
    0.93
     números
    0.93
    字符串
    0.92
    integer
    0.92
     módulo
    0.92
    Act Density 0.455%

    No Known Activations