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

    Neuronpedia

    INDEX
    Explanations

    eye of the beholder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     warehouse
    0.75
     fats
    0.70
     foe
    0.70
     וש
    0.66
    ites
    0.66
     receives
    0.64
    庤
    0.64
     waste
    0.64
     merging
    0.64
     caused
    0.64
    POSITIVE LOGITS
    Eye
    1.11
    eye
    1.06
     eye
    0.96
    But
    0.94
     Eye
    0.92
    Meanwhile
    0.84
    ænd
    0.79
    Bast
    0.78
    眼
    0.77
    astro
    0.75
    Act Density 0.005%

    No Known Activations