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

    Neuronpedia

    INDEX
    Explanations

    Besides, Türkiye, Freeport, trump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    0.78
    로
    0.74
    s
    0.70
    ের
    0.67
    이랑
    0.66
    م
    0.66
    ﺎ
    0.64
    ات
    0.63
    য়ের
    0.62
    ные
    0.62
    POSITIVE LOGITS
    -}$
    0.59
     trump
    0.58
     impressively
    0.54
     Selain
    0.54
    এছাড়া
    0.53
     גם
    0.53
     यह
    0.52
     Freeport
    0.52
     Türkiye
    0.52
    hampton
    0.52
    Act Density 2.889%

    No Known Activations