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

    Neuronpedia

    INDEX
    Explanations

    in summary, investigate, diverse, article, why, chosen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    િમ
    0.49
     gest
    0.47
    推出
    0.44
     verz
    0.41
    受信
    0.41
    ("
    0.39
    ية
    0.39
    вими
    0.39
     maak
    0.39
     politici
    0.39
    POSITIVE LOGITS
     ある
    0.48
     வரு
    0.47
     स्केल
    0.47
     คูณ
    0.47
     அவசியம்
    0.46
     चाइ
    0.46
     どれ
    0.46
    ม
    0.46
     रॉय
    0.45
     अर्
    0.45
    Act Density 0.000%

    No Known Activations