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

    Neuronpedia

    INDEX
    Explanations

    batch commands and system utilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paddington
    0.88
     Donegal
    0.88
     NSMutable
    0.76
    🚂
    0.75
     railroads
    0.75
     Synod
    0.74
     রেলপথ
    0.74
     Burgess
    0.74
     Port
    0.74
     Trains
    0.72
    POSITIVE LOGITS
     LEC
    0.88
     Tencent
    0.87
     bitch
    0.78
    amethasone
    0.78
     esports
    0.77
    ড়ো
    0.76
     बबल
    0.75
     Corsair
    0.75
     Warcraft
    0.75
    war
    0.74
    Act Density 0.139%

    No Known Activations