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

    Neuronpedia

    INDEX
    Explanations

    application name/context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     App
    0.53
    App
    0.50
     apps
    0.47
     Apps
    0.45
    싹
    0.43
     Appl
    0.43
     aplic
    0.40
     Applied
    0.40
    發生
    0.40
    គួរ
    0.39
    POSITIVE LOGITS
    ंद
    0.38
    idn
    0.38
     प्रस्तावित
    0.38
    ێنی
    0.37
    夊
    0.37
    breast
    0.37
    Desc
    0.36
    tong
    0.36
    alignment
    0.36
    interaction
    0.36
    Act Density 0.001%

    No Known Activations