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

    Neuronpedia

    INDEX
    Explanations

    physical components and placement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ใจ
    0.58
     intellectuals
    0.58
     демокра
    0.56
    人生
    0.52
    誕生日
    0.52
    सरकारी
    0.51
     materialistic
    0.51
    貶
    0.51
     बदनाम
    0.50
    人事
    0.50
    POSITIVE LOGITS
     protruding
    0.98
     recessed
    0.90
     inboard
    0.89
     epoxy
    0.88
     cantilever
    0.88
     fiberglass
    0.86
     flange
    0.85
     plastic
    0.84
     bulkhead
    0.82
     underside
    0.82
    Act Density 0.015%

    No Known Activations