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

    Neuronpedia

    INDEX
    Explanations

    jigsaw puzzle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     leverages
    0.42
    と思
    0.41
     kreat
    0.41
     scripting
    0.40
     creatividad
    0.40
    脚本
    0.39
     derivations
    0.38
    อย่า
    0.38
     शोषण
    0.38
    糸
    0.38
    POSITIVE LOGITS
     puzzle
    1.48
     jigsaw
    1.46
     puzzles
    1.42
    puzzle
    1.32
    Puzzle
    1.30
     Puzzle
    1.24
     puzz
    1.17
     паз
    1.05
    🧩
    1.02
     पजल
    0.96
    Act Density 0.010%

    No Known Activations