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

    Neuronpedia

    INDEX
    Explanations

    it... increasingly/incredibly/difficult

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    est
    1.08
     demais
    1.06
    ed
    1.05
    pped
    1.04
    marin
    0.96
     pois
    0.94
    حال
    0.93
    ণ
    0.93
    mActivity
    0.91
    ну
    0.90
    POSITIVE LOGITS
    же
    1.23
    ن
    1.14
     содержимое
    1.12
     imperative
    1.12
    事實
    1.12
    ई
    1.11
    燵
    1.11
    𒀭
    1.10
    人民政府
    1.09
     Grundlage
    1.09
    Act Density 0.029%

    No Known Activations