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

    Neuronpedia

    INDEX
    Explanations

    sex scene, p-n junction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CA
    0.56
    List
    0.52
    Yahoo
    0.51
    Credit
    0.50
    Number
    0.48
    Memory
    0.48
    NUMBER
    0.48
    Six
    0.48
    Web
    0.47
    Hong
    0.47
    POSITIVE LOGITS
     প্রভাবিত
    0.45
    platten
    0.45
    ্ল্ড
    0.43
     infringing
    0.43
     Planting
    0.43
     TNI
    0.43
     mils
    0.43
    merzen
    0.42
     سوشل
    0.42
     quenching
    0.42
    Act Density 0.003%

    No Known Activations