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

    Neuronpedia

    INDEX
    Explanations

    position, size, and label

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spacerItem
    0.40
    لها
    0.39
     ფორ
    0.39
    డి
    0.38
     формы
    0.37
     columnspan
    0.35
    %',
    0.35
    ahrung
    0.35
     పాల
    0.35
    }%
    0.34
    POSITIVE LOGITS
     label
    0.46
     Groups
    0.39
     fred
    0.39
     oe
    0.39
     O
    0.38
     groups
    0.38
    INI
    0.38
     fashioned
    0.38
    opre
    0.38
     group
    0.38
    Act Density 0.002%

    No Known Activations