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

    Neuronpedia

    INDEX
    Explanations

    clothing, footwear, accessories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지
    0.40
    ।
    0.37
    のもの
    0.34
    ה
    0.34
    ي
    0.34
    In
    0.33
    ล
    0.33
    in
    0.33
    では
    0.32
     של
    0.32
    POSITIVE LOGITS
     SULF
    0.32
     for
    0.31
    🕶
    0.31
    elled
    0.31
     Gloves
    0.31
     gloves
    0.31
    职工
    0.31
    v
    0.31
    ut
    0.30
    ra
    0.30
    Act Density 0.364%

    No Known Activations