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

    Neuronpedia

    INDEX
    Explanations

    local css imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仅仅
    0.37
    anjutkan
    0.36
    Essex
    0.36
    iliated
    0.36
    Went
    0.35
    挽
    0.35
    ダウン
    0.35
    Stencil
    0.35
     लाइब्रेरी
    0.35
    Ig
    0.35
    POSITIVE LOGITS
    App
    0.65
     App
    0.64
    globals
    0.58
     globals
    0.53
    index
    0.51
     index
    0.50
     AppDelegate
    0.44
     inde
    0.43
    кал
    0.41
     الموافق
    0.39
    Act Density 0.002%

    No Known Activations