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

    Neuronpedia

    INDEX
    Explanations

    a before noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    0.35
    び
    0.34
    IB
    0.34
    Differences
    0.33
    大きさ
    0.32
    TOP
    0.32
    される
    0.31
     a
    0.31
    Qué
    0.31
    TER
    0.31
    POSITIVE LOGITS
    ↵
    0.41
    il
    0.41
    in
    0.40
    ir
    0.38
    le
    0.36
    ่
    0.36
    ine
    0.34
     కీల
    0.34
     Mikolai
    0.33
    erà
    0.32
    Act Density 0.274%

    No Known Activations