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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers and order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.81
    र
    0.76
    en
    0.71
    ോധ
    0.68
    恫
    0.68
    erweise
    0.66
     severely
    0.66
     karş
    0.65
    ه
    0.65
    ни
    0.63
    POSITIVE LOGITS
     graders
    1.92
     century
    1.76
     baseman
    1.73
     grader
    1.51
     trimester
    1.47
     Century
    1.43
     முறையாக
    1.37
    century
    1.34
     instar
    1.33
     anniversary
    1.30
    Act Density 0.182%

    No Known Activations