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

    Neuronpedia

    INDEX
    Explanations

    far-, increasingly-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     objective
    0.41
     tiden
    0.41
     objectif
    0.41
    ক্লো
    0.41
     objetivo
    0.40
     aim
    0.39
    Generator
    0.38
     поги
    0.38
    >');
    0.38
     sửa
    0.38
    POSITIVE LOGITS
    LLING
    0.40
     Roe
    0.40
     Dominicana
    0.39
     Econ
    0.39
    careers
    0.39
     jurusan
    0.38
    科目
    0.37
    謦
    0.37
    cester
    0.37
     বাধ্যতামূলক
    0.37
    Act Density 0.001%

    No Known Activations