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

    Neuronpedia

    INDEX
    Explanations

    "query" delimited phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ম
    0.48
    ASTER
    0.45
     memorize
    0.44
    iawan
    0.44
    memor
    0.44
     ND
    0.43
     rele
    0.43
     молоко
    0.43
     mourn
    0.43
     scars
    0.42
    POSITIVE LOGITS
    եք
    0.45
    ப்பும்
    0.42
    ுகளை
    0.42
    屆
    0.42
    cü
    0.41
    тый
    0.40
    ுகளில்
    0.40
     অভিন
    0.39
    wek
    0.39
    glichkeiten
    0.39
    Act Density 0.002%

    No Known Activations