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

    Neuronpedia

    INDEX
    Explanations

    location or presence within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refrigerators
    0.38
     helpers
    0.37
     WILLIAMS
    0.35
     adapters
    0.35
     corresponding
    0.35
     competitors
    0.35
     duplicates
    0.34
     neutrals
    0.34
     अल्ट्रा
    0.34
    cocks
    0.34
    POSITIVE LOGITS
     therein
    2.39
     darin
    2.25
     dedans
    2.08
     فيه
    1.97
     उसमें
    1.95
     فيها
    1.81
     thereon
    1.80
     उसमे
    1.80
     dalamnya
    1.78
     அதில்
    1.77
    Act Density 0.042%

    No Known Activations