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

    Neuronpedia

    INDEX
    Explanations

    th century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     木
    0.43
     ውሃ
    0.43
     здоровья
    0.43
    amp
    0.43
     먹
    0.41
    acky
    0.41
     મી
    0.41
     дър
    0.40
     heading
    0.39
     дерева
    0.39
    POSITIVE LOGITS
     alerting
    0.45
     capitalismo
    0.44
    لی
    0.43
    媇
    0.43
     Aula
    0.43
     sorprend
    0.42
    㳒
    0.42
     errado
    0.42
     Serif
    0.41
     Ministries
    0.41
    Act Density 0.000%

    No Known Activations