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

    Neuronpedia

    INDEX
    Explanations

    possessive noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก็
    0.48
    $.
    0.48
    =
    0.46
    The
    0.46
    "।
    0.46
    Хо
    0.46
    被人
    0.44
    是
    0.43
    を使う
    0.43
    は
    0.43
    POSITIVE LOGITS
     opinión
    0.48
     questi
    0.43
    า
    0.43
     Choice
    0.42
     അവരുടെ
    0.42
     esforços
    0.42
     favorite
    0.41
     own
    0.41
     kanilang
    0.41
     தங்கள்
    0.41
    Act Density 0.065%

    No Known Activations