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

    Neuronpedia

    INDEX
    Explanations

    Galois Fields, structure, bounding box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פא
    0.43
     burglary
    0.42
     unstoppable
    0.40
     glamorous
    0.39
     EXEMPLARY
    0.39
    gelt
    0.39
     vamp
    0.38
     spook
    0.38
     вариантов
    0.38
     Dorchester
    0.38
    POSITIVE LOGITS
    徑
    0.43
     Structure
    0.40
     структуры
    0.40
    窮
    0.40
    Structure
    0.40
     structure
    0.39
    strukt
    0.39
    構造
    0.38
    structures
    0.38
    结构
    0.38
    Act Density 0.000%

    No Known Activations