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

    Neuronpedia

    INDEX
    Explanations

    laws and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.31
    ۔
    0.30
     mindless
    0.29
    0.29
    لان
    0.28
     thes
    0.28
     church
    0.27
    :
    0.27
     heroic
    0.27
     midnight
    0.27
    POSITIVE LOGITS
    ות
    0.35
    ۲
    0.31
    ാമ
    0.28
    on
    0.27
    Ảnh
    0.27
    Regulations
    0.26
    우스
    0.26
    Ingredients
    0.25
    法规
    0.25
    Durch
    0.25
    Act Density 0.188%

    No Known Activations