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

    Neuronpedia

    INDEX
    Explanations

    makes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாரா
    0.46
    时间内
    0.40
     достой
    0.40
     अवधि
    0.39
     ক্রেডিট
    0.39
     ग्रेड
    0.39
     hoja
    0.39
     colabor
    0.38
     Craft
    0.38
     Bla
    0.38
    POSITIVE LOGITS
     infantry
    0.46
    क्ती
    0.43
    husky
    0.42
    只会
    0.42
     comedy
    0.41
    Splash
    0.40
     analogy
    0.40
    comedy
    0.40
    使得
    0.39
     splash
    0.39
    Act Density 0.000%

    No Known Activations