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

    Neuronpedia

    INDEX
    Explanations

    blend of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alternate
    0.88
     distinctions
    0.87
    其
    0.86
    付き
    0.85
    ли
    0.83
    別
    0.83
    те
    0.82
    olate
    0.80
    мет
    0.76
    言い
    0.76
    POSITIVE LOGITS
    在一起
    1.60
     seamlessly
    1.27
    ĵo
    1.20
     esfuerzos
    1.07
    றவு
    1.01
     miteinander
    1.01
     ihop
    1.00
     chặt
    0.98
     بندی
    0.96
    তীর্থ
    0.96
    Act Density 0.454%

    No Known Activations