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

    Neuronpedia

    INDEX
    Explanations

    apples, bananas, chickens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🌐
    0.55
     강력
    0.52
    Fuck
    0.49
    Workflow
    0.49
     mirip
    0.49
     практически
    0.49
     유사
    0.49
     כמו
    0.48
    营收
    0.48
     கட்டமை
    0.48
    POSITIVE LOGITS
     towels
    0.70
     chickens
    0.70
     chocolates
    0.70
     muffins
    0.68
     earrings
    0.66
     candies
    0.66
     sweaters
    0.66
     clothes
    0.66
     necklaces
    0.65
     cakes
    0.64
    Act Density 0.099%

    No Known Activations