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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Schwe
    0.43
    .',
    0.40
     Dump
    0.38
    awner
    0.38
     ',
    0.37
    0.37
    eder
    0.37
     Choice
    0.37
    .",
    0.36
     Stocks
    0.36
    POSITIVE LOGITS
    的時間
    0.43
    probably
    0.43
    ന്റെ
    0.42
     itse
    0.41
    টা
    0.41
    功能的
    0.41
    的問題
    0.41
     باتوں
    0.40
     قریب
    0.40
     wakt
    0.40
    Act Density 0.010%

    No Known Activations