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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    line
    -0.07
    Ware
    -0.07
     Enterprise
    -0.07
    Cop
    -0.07
    .sparse
    -0.06
    children
    -0.06
    .SP
    -0.06
     escaping
    -0.06
     outlets
    -0.06
    uffs
    -0.06
    POSITIVE LOGITS
     심
    0.07
    ToUpper
    0.06
     характ
    0.06
    กรรม
    0.06
    ابل
    0.06
     Він
    0.06
     электри
    0.06
    heck
    0.06
    _));↵
    0.06
    ฎ
    0.06
    Act Density 0.006%

    No Known Activations