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

    Neuronpedia

    INDEX
    Explanations

    family members and ties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beatae
    0.78
     Arab
    0.76
     keluarga
    0.76
    ผิว
    0.74
     प्रशिक्षण
    0.74
     বিশ্লেষণ
    0.72
    ્ષ
    0.72
     lulus
    0.71
    ारण
    0.71
    jih
    0.70
    POSITIVE LOGITS
     members
    1.33
     Members
    1.14
     member
    1.12
    Members
    1.07
    members
    1.06
     MEMBERS
    0.98
    成員
    0.95
     tree
    0.93
    成员
    0.92
    Member
    0.90
    Act Density 0.057%

    No Known Activations