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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.35
    DO
    0.34
     सहित
    0.32
    מח
    0.31
    이며
    0.31
     indicative
    0.30
     galore
    0.30
    V
    0.30
    _
    0.30
    9
    0.30
    POSITIVE LOGITS
     tohoto
    0.45
     dieser
    0.41
     этот
    0.41
     this
    0.40
     О
    0.40
     một
    0.40
     Amerikaanse
    0.39
     этой
    0.39
     هذا
    0.38
     cette
    0.38
    Act Density 2.872%

    No Known Activations