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

    Neuronpedia

    INDEX
    Explanations

    pillows and cushions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    आत्म
    0.44
    ంబేద్కర్
    0.42
     briefings
    0.42
     Silent
    0.40
     silent
    0.40
    Silent
    0.40
    ⵕ
    0.38
    async
    0.38
    silent
    0.38
     nonnegative
    0.38
    POSITIVE LOGITS
     pillows
    0.95
     cushions
    0.89
     cushion
    0.83
     pillow
    0.74
     cushioning
    0.74
     Cushion
    0.69
     cudd
    0.66
    枕
    0.66
     поду
    0.63
     Cush
    0.62
    Act Density 0.030%

    No Known Activations