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

    Neuronpedia

    INDEX
    Explanations

    extracts and processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谒
    0.42
     strikeouts
    0.40
    getWidth
    0.39
     ವೇಳ
    0.39
     travaillons
    0.39
    នៅ
    0.39
     گلوکار
    0.38
    ιστα
    0.38
    моль
    0.38
    щите
    0.38
    POSITIVE LOGITS
     Texts
    0.40
     Chat
    0.37
     texts
    0.37
     Administrative
    0.37
     output
    0.36
     DM
    0.35
    Preprocessing
    0.35
    Print
    0.35
     Archive
    0.35
     फा
    0.34
    Act Density 0.000%

    No Known Activations