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

    Neuronpedia

    INDEX
    Explanations

    one ethnic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resulted
    0.92
     irrigated
    0.90
    ]/
    0.89
     مساء
    0.88
    }_
    0.87
     ૨
    0.86
     _
    0.86
     உயர்த்த
    0.85
    ্জ
    0.85
     olay
    0.85
    POSITIVE LOGITS
    สำหรับ
    1.18
    Standalone
    1.11
    Presets
    1.11
     сайты
    1.10
    Alongside
    1.09
    Nobody
    1.06
     scammers
    1.05
     únicas
    1.04
    Software
    1.04
    Haupt
    1.03
    Act Density 0.001%

    No Known Activations