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

    Neuronpedia

    INDEX
    Explanations

    etched or embedded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     देखेंगे
    0.79
     হয়
    0.77
    増や
    0.77
     menerima
    0.76
    чается
    0.75
     iniciar
    0.75
     نقصان
    0.74
     آتے
    0.73
    会出现
    0.72
     लेती
    0.72
    POSITIVE LOGITS
     embedded
    2.51
     etched
    2.07
     tucked
    2.05
     buried
    2.00
     plastered
    1.96
     nestled
    1.93
    embedded
    1.91
     woven
    1.86
     lodged
    1.85
     engraved
    1.82
    Act Density 0.428%

    No Known Activations