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

    Neuronpedia

    INDEX
    Explanations

    target audiences, quality, and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    زع
    0.48
    ڱ
    0.47
    اله
    0.45
     kanyang
    0.44
    عليه
    0.44
     centenary
    0.44
     گرم
    0.43
     truk
    0.42
    ومه
    0.42
    رام
    0.41
    POSITIVE LOGITS
    ного
    0.47
     Современ
    0.47
     Função
    0.47
     प्योर
    0.46
     Kval
    0.45
     бе
    0.45
     функ
    0.44
     форме
    0.44
     Ста
    0.43
     Москве
    0.43
    Act Density 0.036%

    No Known Activations