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

    Neuronpedia

    INDEX
    Explanations

    parentheses or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.32
     l
    0.30
    :
    0.28
    _
    0.27
     exalt
    0.27
     annak
    0.27
     d
    0.26
     Capp
    0.26
     yin
    0.26
     tin
    0.25
    POSITIVE LOGITS
    厰
    0.33
    ৌজ
    0.32
     ಪ್ರದೇಶ
    0.30
    browserTarget
    0.30
    <blockquote>
    0.29
    𐰑
    0.29
    本日
    0.29
    apayati
    0.29
    मे
    0.29
    জেলার
    0.29
    Act Density 0.000%

    No Known Activations