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

    Neuronpedia

    INDEX
    Explanations

    making API requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يطلع
    0.44
     montrent
    0.43
     الطيب
    0.43
     pubescent
    0.43
     trách
    0.42
    bsite
    0.40
    npmjs
    0.40
    publishing
    0.40
    cer
    0.39
    ម្បី
    0.39
    POSITIVE LOGITS
     `/
    1.13
     '/
    1.06
    ('/
    0.97
    (`/
    0.97
    `/
    0.83
     "/
    0.77
     API
    0.75
    ("/
    0.73
     api
    0.71
     `${
    0.67
    Act Density 0.005%

    No Known Activations