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

    Neuronpedia

    INDEX
    Explanations

    the pronoun his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    她们
    1.78
     elas
    1.59
     juntas
    1.53
     ellas
    1.50
     elles
    1.45
     yourselves
    1.42
     নিজেরাই
    1.41
    டுகின்றன
    1.28
     delas
    1.28
     éstas
    1.27
    POSITIVE LOGITS
     his
    7.16
    his
    6.01
    他的
    5.99
     그의
    5.49
    彼の
    5.47
     его
    5.26
     jego
    5.16
     jeho
    4.98
    His
    4.92
     His
    4.76
    Act Density 0.936%

    No Known Activations