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

    Neuronpedia

    INDEX
    Explanations

    everywhere or throughout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    υχ
    0.66
     complex
    0.64
    명의
    0.63
     কোনও
    0.60
    ländischen
    0.59
     áp
    0.59
     complexe
    0.57
     quale
    0.56
    ighed
    0.56
    länd
    0.55
    POSITIVE LOGITS
     throughout
    1.73
     everywhere
    1.50
     Throughout
    1.38
    Throughout
    1.35
     Everywhere
    1.29
     khắp
    1.06
     elsewhere
    1.04
     THRO
    1.01
    Elsewhere
    0.98
     überall
    0.98
    Act Density 0.143%

    No Known Activations