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

    Neuronpedia

    INDEX
    Explanations

    prepositions of location and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    수인
    0.18
     assigning
    0.17
    acije
    0.17
    相關
    0.16
     descre
    0.16
     enforceable
    0.16
     proportionate
    0.16
    Meng
    0.16
    dis
    0.16
     עבור
    0.16
    POSITIVE LOGITS
     the
    0.27
     onto
    0.23
     outskirts
    0.21
     piles
    0.21
     railings
    0.21
     patio
    0.21
     THE
    0.20
     экрана
    0.20
     billowing
    0.20
     sidewalks
    0.19
    Act Density 0.125%

    No Known Activations