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

    Neuronpedia

    INDEX
    Explanations

    closing parentheses and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वाचा
    0.36
    ymce
    0.35
    níku
    0.34
     bravery
    0.34
    whereas
    0.34
     whereas
    0.33
    urchase
    0.33
     พอ
    0.33
     zunächst
    0.33
     Whereas
    0.33
    POSITIVE LOGITS
    वं
    0.43
     shifting
    0.43
     shifted
    0.42
     Selanjutnya
    0.37
     FISH
    0.37
     Wail
    0.37
     Wab
    0.37
     %#
    0.37
     Chow
    0.36
    SpacerItem
    0.35
    Act Density 0.016%

    No Known Activations